# Ultralytics YOLO 🚀, AGPL-3.0 license

import numpy as np
import math

from ..utils import LOGGER
from ..utils.ops import xywh2ltwh, xywh2xyxy
from .basetrack import BaseTrack, TrackState
from .utils import matching
from .utils.kalman_filter import KalmanFilterXYAH


class STrack(BaseTrack):
    """
    Single object tracking representation that uses Kalman filtering for state estimation.

    This class is responsible for storing all the information regarding individual tracklets and performs state updates
    and predictions based on Kalman filter.

    Attributes:
        shared_kalman (KalmanFilterXYAH): Shared Kalman filter that is used across all STrack instances for prediction.
        _tlwh (np.ndarray): Private attribute to store top-left corner coordinates and width and height of bounding box.
        kalman_filter (KalmanFilterXYAH): Instance of Kalman filter used for this particular object track.
        mean (np.ndarray): Mean state estimate vector.
        covariance (np.ndarray): Covariance of state estimate.
        is_activated (bool): Boolean flag indicating if the track has been activated.
        score (float): Confidence score of the track.
        tracklet_len (int): Length of the tracklet.
        cls (any): Class label for the object.
        idx (int): Index or identifier for the object.
        frame_id (int): Current frame ID.
        start_frame (int): Frame where the object was first detected.

    Methods:
        predict(): Predict the next state of the object using Kalman filter.
        multi_predict(stracks): Predict the next states for multiple tracks.
        multi_gmc(stracks, H): Update multiple track states using a homography matrix.
        activate(kalman_filter, frame_id): Activate a new tracklet.
        re_activate(new_track, frame_id, new_id): Reactivate a previously lost tracklet.
        update(new_track, frame_id): Update the state of a matched track.
        convert_coords(tlwh): Convert bounding box to x-y-aspect-height format.
        tlwh_to_xyah(tlwh): Convert tlwh bounding box to xyah format.
    """

    shared_kalman = KalmanFilterXYAH()

    def __init__(self, xywh, score, cls):
        """Initialize new STrack instance."""
        super().__init__()
        # xywh+idx or xywha+idx
        assert len(xywh) in {5, 6}, f"expected 5 or 6 values but got {len(xywh)}"
        self._tlwh = np.asarray(xywh2ltwh(xywh[:4]), dtype=np.float32)
        self.kalman_filter = None
        self.mean, self.covariance = None, None
        self.is_activated = False

        self.score = score
        self.tracklet_len = 0
        self.cls = cls
        self.idx = xywh[-1]
        self.angle = xywh[4] if len(xywh) == 6 else None

        self.det = np.asarray(xywh2xyxy(xywh[:4]), dtype=np.float32)

        self.recent_scores = []  # 用于存储最近10次的score
        self.recent_scores.append(self.score)
        self.tracklet_len_score = self.score

    def predict(self):
        """Predicts mean and covariance using Kalman filter."""
        mean_state = self.mean.copy()
        if self.state != TrackState.Tracked:
            mean_state[7] = 0
        self.mean, self.covariance = self.kalman_filter.predict(mean_state, self.covariance)

    def prior_predict(self):
        """Predicts mean and covariance using Kalman filter."""
        mean_state = self.mean.copy()
        if self.state != TrackState.Tracked:
            return None
        mean, covariance = self.kalman_filter.predict(mean_state, self.covariance)
        return mean

    @staticmethod
    def multi_predict(stracks):
        """Perform multi-object predictive tracking using Kalman filter for given stracks."""
        if len(stracks) <= 0:
            return
        multi_mean = np.asarray([st.mean.copy() for st in stracks])
        multi_covariance = np.asarray([st.covariance for st in stracks])
        for i, st in enumerate(stracks):
            if st.state != TrackState.Tracked:
                multi_mean[i][7] = 0
        multi_mean, multi_covariance = STrack.shared_kalman.multi_predict(multi_mean, multi_covariance)
        for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
            stracks[i].mean = mean
            stracks[i].covariance = cov

    @staticmethod
    def multi_gmc(stracks, H=np.eye(2, 3)):
        """Update state tracks positions and covariances using a homography matrix."""
        if len(stracks) > 0:
            multi_mean = np.asarray([st.mean.copy() for st in stracks])
            multi_covariance = np.asarray([st.covariance for st in stracks])

            R = H[:2, :2]
            R8x8 = np.kron(np.eye(4, dtype=float), R)
            t = H[:2, 2]

            for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
                mean = R8x8.dot(mean)
                mean[:2] += t
                cov = R8x8.dot(cov).dot(R8x8.transpose())

                stracks[i].mean = mean
                stracks[i].covariance = cov

    def activate(self, kalman_filter, frame_id):
        """Start a new tracklet."""
        self.kalman_filter = kalman_filter
        self.track_id = self.next_id()
        self.mean, self.covariance = self.kalman_filter.initiate(self.convert_coords(self._tlwh))

        self.tracklet_len = 0
        self.state = TrackState.Tracked
        if frame_id == 1:
            self.is_activated = True
        self.frame_id = frame_id
        self.start_frame = frame_id

    def re_activate(self, new_track, frame_id, new_id=False):
        """Reactivates a previously lost track with a new detection."""
        self.mean, self.covariance = self.kalman_filter.update(
            self.mean, self.covariance, self.convert_coords(new_track.tlwh)
        )
        self.tracklet_len = 0
        self.state = TrackState.Tracked
        self.is_activated = True
        self.frame_id = frame_id
        if new_id:
            self.track_id = self.next_id()
        self.score = new_track.score
        self.cls = new_track.cls
        self.angle = new_track.angle
        self.idx = new_track.idx

        self.det = new_track.xyxy

        self.recent_scores = [] # re clear
        self.recent_scores.append(self.score)
        self.tracklet_len_score = self.score

    def update(self, new_track, frame_id):
        """
        Update the state of a matched track.

        Args:
            new_track (STrack): The new track containing updated information.
            frame_id (int): The ID of the current frame.
        """
        self.frame_id = frame_id
        self.tracklet_len += 1

        new_tlwh = new_track.tlwh
        self.mean, self.covariance = self.kalman_filter.update(
            self.mean, self.covariance, self.convert_coords(new_tlwh)
        )
        self.state = TrackState.Tracked
        self.is_activated = True

        self.score = new_track.score
        self.cls = new_track.cls
        self.angle = new_track.angle
        self.idx = new_track.idx

        self.det = new_track.xyxy

        self.recent_scores.append(self.score)
        if len(self.recent_scores) > 10:
            self.recent_scores.pop(0)  
        self.tracklet_len_score = sum(self.recent_scores)

    def update_simi(self, new_track, frame_id):
        """
        Update the state of a matched track.

        Args:
            new_track (STrack): The new track containing updated information.
            frame_id (int): The ID of the current frame.
        """
        self.frame_id = frame_id
        self.tracklet_len += 1

        # 认为存在突变
        new_tlwh = new_track.tlwh
        self.mean, self.covariance = self.kalman_filter.initiate(self.convert_coords(new_tlwh))
        self.state = TrackState.Tracked
        self.is_activated = True

        self.score = new_track.score
        self.cls = new_track.cls
        self.angle = new_track.angle
        self.idx = new_track.idx

        self.det = new_track.xyxy

        self.recent_scores.append(self.score)
        if len(self.recent_scores) > 10:
            self.recent_scores.pop(0)  
        self.tracklet_len_score = sum(self.recent_scores)

    def convert_coords(self, tlwh):
        """Convert a bounding box's top-left-width-height format to its x-y-aspect-height equivalent."""
        return self.tlwh_to_xyah(tlwh)

    @property
    def tlwh(self):
        """Get current position in bounding box format (top left x, top left y, width, height)."""
        if self.mean is None:
            return self._tlwh.copy()
        ret = self.mean[:4].copy()
        ret[2] *= ret[3]
        ret[:2] -= ret[2:] / 2
        return ret

    @property
    def xyxy(self):
        """Convert bounding box to format (min x, min y, max x, max y), i.e., (top left, bottom right)."""
        ret = self.tlwh.copy()
        ret[2:] += ret[:2]
        return ret

    @staticmethod
    def tlwh_to_xyah(tlwh):
        """Convert bounding box to format (center x, center y, aspect ratio, height), where the aspect ratio is width /
        height.
        """
        ret = np.asarray(tlwh).copy()
        ret[:2] += ret[2:] / 2
        ret[2] /= ret[3]
        return ret

    @property
    def xywh(self):
        """Get current position in bounding box format (center x, center y, width, height)."""
        ret = np.asarray(self.tlwh).copy()
        ret[:2] += ret[2:] / 2
        return ret

    @property
    def xywha(self):
        """Get current position in bounding box format (center x, center y, width, height, angle)."""
        if self.angle is None:
            LOGGER.warning("WARNING ⚠️ `angle` attr not found, returning `xywh` instead.")
            return self.xywh
        return np.concatenate([self.xywh, self.angle[None]])

    @property
    def result(self):
        """Get current tracking results."""
        coords = self.xyxy if self.angle is None else self.xywha
        return coords.tolist() + [self.track_id, self.score, self.cls, self.idx]

    def __repr__(self):
        """Return a string representation of the SOTTracker object with start and end frames and track ID."""
        return f"OT_{self.track_id}_({self.start_frame}-{self.end_frame})"


class SOTTracker:
    """
    SOTTracker: A tracking algorithm built on top of YOLOv8 for object detection and tracking.

    The class is responsible for initializing, updating, and managing the tracks for detected objects in a video
    sequence. It maintains the state of tracked, lost, and removed tracks over frames, utilizes Kalman filtering for
    predicting the new object locations, and performs data association.

    Attributes:
        tracked_stracks (list[STrack]): List of successfully activated tracks.
        lost_stracks (list[STrack]): List of lost tracks.
        removed_stracks (list[STrack]): List of removed tracks.
        frame_id (int): The current frame ID.
        args (namespace): Command-line arguments.
        max_time_lost (int): The maximum frames for a track to be considered as 'lost'.
        kalman_filter (object): Kalman Filter object.

    Methods:
        update(results, img=None): Updates object tracker with new detections.
        get_kalmanfilter(): Returns a Kalman filter object for tracking bounding boxes.
        init_track(dets, scores, cls, img=None): Initialize object tracking with detections.
        get_dists(tracks, detections): Calculates the distance between tracks and detections.
        multi_predict(tracks): Predicts the location of tracks.
        reset_id(): Resets the ID counter of STrack.
        joint_stracks(tlista, tlistb): Combines two lists of stracks.
        sub_stracks(tlista, tlistb): Filters out the stracks present in the second list from the first list.
        remove_duplicate_stracks(stracksa, stracksb): Removes duplicate stracks based on IoU.
    """

    def __init__(self, args, frame_rate=30):
        """Initialize a YOLOv8 object to track objects with given arguments and frame rate."""
        self.tracked_stracks = []  # type: list[STrack]
        self.lost_stracks = []  # type: list[STrack]
        self.removed_stracks = []  # type: list[STrack]

        self.frame_id = 0
        self.args = args
        self.max_time_lost = int(frame_rate / 30.0 * args.track_buffer)
        self.kalman_filter = self.get_kalmanfilter()
        self.reset_id()
        self.prior_strack = None

    def update(self, results, img=None):
        """Updates object tracker with new detections and returns tracked object bounding boxes."""
        self.frame_id += 1
        self.prior_strack = None
        activated_stracks = []
        refind_stracks = []
        lost_stracks = []
        removed_stracks = []

        scores = results.conf
        bboxes = results.xywhr if hasattr(results, "xywhr") else results.xywh
        # Add index
        bboxes = np.concatenate([bboxes, np.arange(len(bboxes)).reshape(-1, 1)], axis=-1)
        cls = results.cls

        # if scores[0] < 0.1: # note:当box为0时IOU为1
        #     return np.asarray([])

        # Add newly detected tracklets to tracked_stracks
        unconfirmed = []
        tracked_stracks = []  # type: list[STrack]
        for track in self.tracked_stracks:
            if not track.is_activated:
                unconfirmed.append(track)
            else:
                tracked_stracks.append(track)
        strack_pool = self.joint_stracks(tracked_stracks, self.lost_stracks)
        # Predict the current location with KF
        self.multi_predict(strack_pool) # important for correct state
        if hasattr(self, "gmc") and img is not None:
            warp = self.gmc.apply(img, dets)
            STrack.multi_gmc(strack_pool, warp)
            STrack.multi_gmc(unconfirmed, warp)

        # step 000 for sot
        prior_strack = None
        prior_update_id = -1
        candidate_det = None
        len_max = 0
        # 寻找优势目标
        # 优先在激活目标中寻找
        for track in self.tracked_stracks:
            if track.tracklet_len_score > max(len_max, 5):
                prior_strack = track
                len_max = track.tracklet_len_score
        # 没有则在短时丢失目标中寻找
        if prior_strack is None:
            for track in self.lost_stracks:
                if track.tracklet_len_score > max(len_max, 5):
                    prior_strack = track
                    len_max = track.tracklet_len_score
        # 存在优势目标后进行匹配
        if prior_strack is not None:
            sot_detections = self.init_track(bboxes, scores, cls, img)
            simi_dists = self.get_simi_dists([prior_strack], sot_detections)
            iou_dists = matching.iou_distance([prior_strack], sot_detections)
            # idet = np.argmax(iou_dists)
            # if iou_dists[0, idet] > 0.5: # note:当box为0时IOU为1
            #     prior_strack.update(sot_detections[idet], self.frame_id)
            #     activated_stracks.append(prior_strack)
            #     prior_update_id = idet
            # elif simi_dists.max() > 0.6: # IOU计算替换:
            #     # 置信度较高则直接更新
            #     if sot_detections[idet].score > 0.3: 
            #         prior_strack.update_simi(sot_detections[idet], self.frame_id)
            #         activated_stracks.append(prior_strack)
            #         prior_update_id = idet
            #     # 置信度较低则采用更严格匹配
            #     else:
            #         candidate_det = sot_detections[idet] # track_id
            #         candidate_det.track_id = prior_strack.track_id
            idet = np.argmax(simi_dists)
            if simi_dists.max() > 0.6: # IOU计算替换
                # 置信度较高则直接更新
                if iou_dists[0, idet] > 0.5:
                    prior_strack.update(sot_detections[idet], self.frame_id)
                    activated_stracks.append(prior_strack)
                    prior_update_id = idet
                else:
                    if sot_detections[idet].score > 0.2: # 0.3
                        prior_strack.update_simi(sot_detections[idet], self.frame_id)
                        activated_stracks.append(prior_strack)
                        prior_update_id = idet
                    # 置信度较低则采用更严格匹配
                    else:
                        candidate_det = sot_detections[idet] # track_id
                        candidate_det.track_id = prior_strack.track_id

        if prior_update_id != -1: 
            scores[idet] = 0 # for sot
        remain_inds = scores >= self.args.track_high_thresh
        inds_low = scores > self.args.track_low_thresh
        inds_high = scores < self.args.track_high_thresh

        inds_second = inds_low & inds_high
        dets_second = bboxes[inds_second]
        dets = bboxes[remain_inds]
        scores_keep = scores[remain_inds]
        scores_second = scores[inds_second]
        cls_keep = cls[remain_inds]
        cls_second = cls[inds_second]

        # Step 2: First association, with high score detection boxes
        detections = self.init_track(dets, scores_keep, cls_keep, img)
        if prior_update_id != -1:
            strack_pool = self.sub_stracks(strack_pool, [prior_strack]) # for sot
        dists = self.get_dists(strack_pool, detections)
        matches, u_track, u_detection = matching.linear_assignment(dists, thresh=self.args.match_thresh)

        for itracked, idet in matches:
            track = strack_pool[itracked]
            det = detections[idet]
            if track.state == TrackState.Tracked:
                track.update(det, self.frame_id)
                activated_stracks.append(track)
            else:
                track.re_activate(det, self.frame_id, new_id=False)
                refind_stracks.append(track)
        # Step 3: Second association, with low score detection boxes association the untrack to the low score detections
        detections_second = self.init_track(dets_second, scores_second, cls_second, img)
        r_tracked_stracks = [strack_pool[i] for i in u_track if strack_pool[i].state == TrackState.Tracked]
        # TODO
        dists = matching.iou_distance(r_tracked_stracks, detections_second)
        matches, u_track, u_detection_second = matching.linear_assignment(dists, thresh=0.5)
        for itracked, idet in matches:
            track = r_tracked_stracks[itracked]
            det = detections_second[idet]
            if track.state == TrackState.Tracked:
                track.update(det, self.frame_id)
                activated_stracks.append(track)
            else:
                track.re_activate(det, self.frame_id, new_id=False)
                refind_stracks.append(track)

        for it in u_track:
            track = r_tracked_stracks[it]
            if track.state != TrackState.Lost:
                track.mark_lost()
                lost_stracks.append(track)
        # Deal with unconfirmed tracks, usually tracks with only one beginning frame
        detections = [detections[i] for i in u_detection]
        dists = self.get_dists(unconfirmed, detections)
        matches, u_unconfirmed, u_detection = matching.linear_assignment(dists, thresh=0.7)
        for itracked, idet in matches:
            unconfirmed[itracked].update(detections[idet], self.frame_id)
            activated_stracks.append(unconfirmed[itracked])
        for it in u_unconfirmed:
            track = unconfirmed[it]
            track.mark_removed()
            removed_stracks.append(track)
        # Step 4: Init new stracks
        for inew in u_detection:
            track = detections[inew]
            if track.score < self.args.new_track_thresh:
                continue
            track.activate(self.kalman_filter, self.frame_id)
            activated_stracks.append(track)
        # Step 5: Update state
        for track in self.lost_stracks:
            if self.frame_id - track.end_frame > self.max_time_lost:
                track.mark_removed()
                removed_stracks.append(track)

        self.tracked_stracks = [t for t in self.tracked_stracks if t.state == TrackState.Tracked]
        self.tracked_stracks = self.joint_stracks(self.tracked_stracks, activated_stracks)
        self.tracked_stracks = self.joint_stracks(self.tracked_stracks, refind_stracks)
        self.lost_stracks = self.sub_stracks(self.lost_stracks, self.tracked_stracks)
        self.lost_stracks.extend(lost_stracks)
        self.lost_stracks = self.sub_stracks(self.lost_stracks, self.removed_stracks)
        self.tracked_stracks, self.lost_stracks = self.remove_duplicate_stracks(self.tracked_stracks, self.lost_stracks)
        self.removed_stracks.extend(removed_stracks)
        if len(self.removed_stracks) > 1000:
            self.removed_stracks = self.removed_stracks[-999:]  # clip remove stracks to 1000 maximum

        # 当多个目标时：只输出优先目标
        # 当没有可靠目标但有检测时：输出simi最相似的目标
        prior_strack = None
        len_max = -1
        for track in self.tracked_stracks:
            if track.state == TrackState.Tracked and track.tracklet_len_score > len_max:
                prior_strack = track
                len_max = track.tracklet_len_score
        # 初始化点置信度将为0.25，按轨迹长度进行置信度分级，并采用轨迹加权以减轻一直误检影响
        score_max = 0
        if prior_strack is not None and prior_strack.tracklet_len_score < 1:
            for track in self.tracked_stracks: #选出置信度最高
                if track.state == TrackState.Tracked and track.score > score_max: 
                    prior_strack = track
                    score_max = track.score
            if prior_strack.score < 0.6:
                prior_strack = None
        if prior_strack is not None:
            self.prior_strack = prior_strack
            return np.asarray([prior_strack.det.tolist()+prior_strack.result[-4:]], dtype=np.float32) # result为滤波调整后
        elif candidate_det is not None:
            return np.asarray([candidate_det.result], dtype=np.float32)
        else:
            # valid_indices = np.where(scores > 0)[0]  
            # if valid_indices.size > 0:
            #     max_idx = valid_indices[np.argmax(scores[valid_indices])]
            #     out_det = STrack(bboxes[max_idx], scores[max_idx], cls[max_idx])
            #     return np.asarray([out_det.result], dtype=np.float32)
            return np.asarray([])

        # return np.asarray([x.result for x in self.tracked_stracks if x.is_activated], dtype=np.float32)

    def prior_predict(self):
        """Returns a Kalman filter object for tracking bounding boxes."""
        if self.prior_strack is not None:
            return self.prior_strack.prior_predict()
        return None
    
    def multi_gmc(self, warp):
        STrack.multi_gmc(self.tracked_stracks, warp)
        STrack.multi_gmc(self.lost_stracks, warp)
    
    def get_kalmanfilter(self):
        """Returns a Kalman filter object for tracking bounding boxes."""
        return KalmanFilterXYAH()

    def init_track(self, dets, scores, cls, img=None):
        """Initialize object tracking with detections and scores using STrack algorithm."""
        return [STrack(xyxy, s, c) for (xyxy, s, c) in zip(dets, scores, cls)] if len(dets) else []  # detections

    def get_dists(self, tracks, detections):
        """Calculates the distance between tracks and detections using IoU and fuses scores."""
        dists = matching.iou_distance(tracks, detections)
        # TODO: mot20
        # if not self.args.mot20:
        dists = matching.fuse_score(dists, detections)
        return dists
    
    def get_simi_dists(self, tracks, detections):
        """Calculates the distance between tracks and detections using IoU and fuses scores."""
        dists = self.simi_distance(tracks, detections)
        return dists

    def multi_predict(self, tracks):
        """Returns the predicted tracks using the YOLOv8 network."""
        STrack.multi_predict(tracks)

    @staticmethod
    def reset_id():
        """Resets the ID counter of STrack."""
        STrack.reset_id()

    def reset(self):
        """Reset tracker."""
        self.tracked_stracks = []  # type: list[STrack]
        self.lost_stracks = []  # type: list[STrack]
        self.removed_stracks = []  # type: list[STrack]
        self.frame_id = 0
        self.kalman_filter = self.get_kalmanfilter()
        self.reset_id()

    @staticmethod
    def joint_stracks(tlista, tlistb):
        """Combine two lists of stracks into a single one."""
        exists = {}
        res = []
        for t in tlista:
            exists[t.track_id] = 1
            res.append(t)
        for t in tlistb:
            tid = t.track_id
            if not exists.get(tid, 0):
                exists[tid] = 1
                res.append(t)
        return res

    @staticmethod
    def sub_stracks(tlista, tlistb):
        """DEPRECATED CODE in https://github.com/ultralytics/ultralytics/pull/1890/
        stracks = {t.track_id: t for t in tlista}
        for t in tlistb:
            tid = t.track_id
            if stracks.get(tid, 0):
                del stracks[tid]
        return list(stracks.values())
        """
        track_ids_b = {t.track_id for t in tlistb}
        return [t for t in tlista if t.track_id not in track_ids_b]

    @staticmethod
    def remove_duplicate_stracks(stracksa, stracksb):
        """Remove duplicate stracks with non-maximum IoU distance."""
        pdist = matching.iou_distance(stracksa, stracksb)
        pairs = np.where(pdist < 0.15)
        dupa, dupb = [], []
        for p, q in zip(*pairs):
            timep = stracksa[p].frame_id - stracksa[p].start_frame
            timeq = stracksb[q].frame_id - stracksb[q].start_frame
            if timep > timeq:
                dupb.append(q)
            else:
                dupa.append(p)
        resa = [t for i, t in enumerate(stracksa) if i not in dupa]
        resb = [t for i, t in enumerate(stracksb) if i not in dupb]
        return resa, resb

    @staticmethod
    def simi_distance(atracks: list, btracks: list) -> np.ndarray:
        """
        Compute cost based on Intersection over Union (IoU) between tracks.

        Args:
            atracks (list[STrack] | list[np.ndarray]): List of tracks 'a' or bounding boxes.
            btracks (list[STrack] | list[np.ndarray]): List of tracks 'b' or bounding boxes.

        Returns:
            (np.ndarray): Cost matrix computed based on IoU.
        """

        if atracks and isinstance(atracks[0], np.ndarray) or btracks and isinstance(btracks[0], np.ndarray):
            atlbrs = atracks
            btlbrs = btracks
        else:
            atlbrs = [track.xywha if track.angle is not None else track.xyxy for track in atracks]
            btlbrs = [track.xywha if track.angle is not None else track.xyxy for track in btracks]

        simi = np.zeros((len(atlbrs), len(btlbrs)), dtype=np.float32)
        if len(atlbrs) and len(btlbrs):
            simi = SOTTracker.bbox_simi(
                    np.ascontiguousarray(atlbrs, dtype=np.float32),
                    np.ascontiguousarray(btlbrs, dtype=np.float32),
                    )
        return 1 - simi  # cost matrix
    
    @staticmethod
    def bbox_simi(box1, box2, eps=1e-7):
        """
        Calculate the intersection over box2 area given box1 and box2. Boxes are in x1y1x2y2 format.

        Args:
            box1 (np.ndarray): A numpy array of shape (n, 4) representing n bounding boxes.
            box2 (np.ndarray): A numpy array of shape (m, 4) representing m bounding boxes.
            iou (bool): Calculate the standard IoU if True else return inter_area/box2_area.
            eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7.

        Returns:
            (np.ndarray): A numpy array of shape (n, m) representing the intersection over box2 area.
        """

        # Get the coordinates of bounding boxes
        b1_x1, b1_y1, b1_x2, b1_y2 = box1.T
        b2_x1, b2_y1, b2_x2, b2_y2 = box2.T
        cx1 = (b1_x1 + b1_x2) / 2
        cy1 = (b1_y1 + b1_y2) / 2
        cx2 = (b2_x1 + b2_x2) / 2
        cy2 = (b2_y1 + b2_y2) / 2
        w1 = b1_x2 - b1_x1
        h1 = b1_y2 - b1_y1
        w2 = b2_x2 - b2_x1
        h2 = b2_y2 - b2_y1
        cw = np.maximum(b1_x2,b2_x2) - np.minimum(b1_x1,b2_x1)  # convex (smallest enclosing box) width
        ch = np.maximum(b1_y2,b2_y2) - np.minimum(b1_y1,b2_y1)  # convex height

        # shape = abs(w1*h1-w2*h2) + abs(w1*h2-w2*h1)
        # dis = (cx1 - cx2)**2 + (cy1 - cy2)**2

        shape = 0.5*np.abs(w1*h1-w2*h2)/(np.maximum(w1*h1,w2*h2)+eps) + 0.5*np.abs(w1*h2-w2*h1)/(np.maximum(w1*h2,w2*h1)+eps)
        dis = np.sqrt((cx1 - cx2)**2 + (cy1 - cy2)**2) / (np.sqrt(cw**2 + ch**2) + eps)

        simi = shape * 0.8 + dis * 0.2

        # if shape.shape[0] > 1:
        #     print(simi)

        return simi