Deepsort + Yolo 实现行人检测和轨迹追踪的方法

def yolo_body(inputs, num_anchors, num_classes):
    """Create YOLO_V3 model CNN body in Keras."""
    darknet = Model(inputs, darknet_body(inputs))
    x, y1 = make_last_layers(darknet.output, 512, num_anchors*(num_classes+5))
    x = compose(
            DarknetConv2D_BN_Leaky(256, (1,1)),
            UpSampling2D(2))(x)
    x = Concatenate()([x,darknet.layers[152].output])
    x, y2 = make_last_layers(x, 256, num_anchors*(num_classes+5))
    x = compose(
            DarknetConv2D_BN_Leaky(128, (1,1)),
            UpSampling2D(2))(x)
    x = Concatenate()([x,darknet.layers[92].output])
    x, y3 = make_last_layers(x, 128, num_anchors*(num_classes+5))
    return Model(inputs, [y1,y2,y3])

def Update(self, detections):
    if (len(self.tracks) == 0):
        for i in range(len(detections)):
            track = Track(detections[i], self.trackIdCount)
            self.trackIdCount += 1
            self.tracks.append(track)
    N = len(self.tracks)
    M = len(detections)
    cost = np.zeros(shape=(N, M)) 
    for i in range(len(self.tracks)):
        for j in range(len(detections)):
            try:
                diff = self.tracks[i].prediction - detections[j]
                distance = np.sqrt(diff[0][0]*diff[0][0] +
                                   diff[1][0]*diff[1][0])
                cost[i][j] = distance
            except:
                pass
    cost = (0.5) * cost
    assignment = []
    for _ in range(N):
        assignment.append(-1)
    row_ind, col_ind = linear_sum_assignment(cost)
    for i in range(len(row_ind)):
        assignment[row_ind[i]] = col_ind[i]
    un_assigned_tracks = []
    for i in range(len(assignment)):
        if (assignment[i] != -1):
            if (cost[i][assignment[i]] > self.dist_thresh):
                assignment[i] = -1
                un_assigned_tracks.append(i)
            pass
        else:
            self.tracks[i].skipped_frames += 1
    del_tracks = []

track_colors = get_colors_for_classes(max_colors)
result = np.asarray(image)
font = cv2.FONT_HERSHEY_SIMPLEX
result0 = result.copy()
result1=result.copy()
img_position=np.zeros([result.shape[0],result.shape[1],3])
if (len(centers) > 0):
    tracker.Update(centers)
    for i in range(len(tracker.tracks)):
        if (len(tracker.tracks[i].trace) > 1):
            x0, y0 = tracker.tracks[i].trace[-1][0][0], tracker.tracks[i].trace[-1][1][0]
            cv2.putText(result0, "ID: "+str(tracker.tracks[i].track_id-99), (int(x0), int(y0)), font, track_id_size,
                        (255, 255, 255), 2)
            cv2.putText(result1, "ID: " + str(tracker.tracks[i].track_id - 99), (int(x0), int(y0)), font,
                        track_id_size,
                        (255, 255, 255), 2)
            color_random = tracker.tracks[i].track_id % 9
            cv2.circle(img_position, (int(x0), int(y0)), 1, track_colors[color_random], 8)
            cv2.putText(img_position, str(tracker.tracks[i].track_id - 99), (int(x0), int(y0)), font,
                        track_id_size,
                        (255, 255, 255), 2)
            result0=result0.copy()
            for j in range(len(tracker.tracks[i].trace) - 1):
                x1 = tracker.tracks[i].trace[j][0][0]
                y1 = tracker.tracks[i].trace[j][1][0]
                x2 = tracker.tracks[i].trace[j + 1][0][0]
                y2 = tracker.tracks[i].trace[j + 1][1][0]
                clr = tracker.tracks[i].track_id % 9
                distance = ((x2 - x1) ** 2 + (y2 - y1) ** 2) ** 0.5
                if distance < max_point_distance:
                    cv2.line(result1, (int(x1), int(y1)), (int(x2), int(y2)),
                             track_colors[clr], 4)
            result1=result1.copy()