detect_track_timedwell.py

import argparse
import os
import platform
import shutil
import time
import datetime
from pathlib import Path

import cv2
import torch
import torch.backends.cudnn as cudnn
from numpy import random

from utils.google_utils import attempt_load
from utils.datasets import LoadStreams, LoadImages
from utils.general import (
    check_img_size, non_max_suppression, apply_classifier, scale_coords, xyxy2xywh, strip_optimizer)
from utils.plots import plot_one_box
from utils.torch_utils import select_device, load_classifier, time_synchronized

from models.models import *
from utils.datasets import *
from utils.general import *

from deep_sort_pytorch.utils.parser import get_config
from deep_sort_pytorch.deep_sort import DeepSort
from collections import deque


palette = (2 ** 11 - 1, 2 ** 15 - 1, 2 ** 20 - 1)

fps_start_time = datetime.datetime.now()
fps = 0
total_frames = 0

#object_id_list = []
dtime = dict()
dwell_time = dict()

data_deque = {}
#time_deque = {}

def xyxy_to_xywh(*xyxy):
    """" Calculates the relative bounding box from absolute pixel values. """
    bbox_left = min([xyxy[0].item(), xyxy[2].item()])
    bbox_top = min([xyxy[1].item(), xyxy[3].item()])
    bbox_w = abs(xyxy[0].item() - xyxy[2].item())
    bbox_h = abs(xyxy[1].item() - xyxy[3].item())
    x_c = (bbox_left + bbox_w / 2)
    y_c = (bbox_top + bbox_h / 2)
    w = bbox_w
    h = bbox_h
    return x_c, y_c, w, h

def xyxy_to_tlwh(bbox_xyxy):
    tlwh_bboxs = []
    for i, box in enumerate(bbox_xyxy):
        x1, y1, x2, y2 = [int(i) for i in box]
        top = x1
        left = y1
        w = int(x2 - x1)
        h = int(y2 - y1)
        tlwh_obj = [top, left, w, h]
        tlwh_bboxs.append(tlwh_obj)
    return tlwh_bboxs


def compute_color_for_labels(label):
    """
    Simple function that adds fixed color depending on the class
    """
    color = [int((p * (label ** 2 - label + 1)) % 255) for p in palette]
    return tuple(color)

def draw_boxes(img, bbox, identities=None, offset=(0, 0)):
    # print(len(identities))
    # print(type(identities))

    # remove tracked point from buffer if object is lost
    for key in list(data_deque):
      if key not in identities:
        data_deque.pop(key)

    for i, box in enumerate(bbox):
        # print("box muner", i)
        x1, y1, x2, y2 = [int(i) for i in box]
        x1 += offset[0]
        x2 += offset[0]
        y1 += offset[1]
        y2 += offset[1]
        
        # code to find center of bottom edge
        center = (int((x2+x1)/ 2), int((y2+y2)/2))
        # draw circle at center
        cv2.circle(img, center, 5, (0, 0, 255), -1)
        # pts.appendleft(center)
        # deque[key].appendleft(center)

        # get ID of object
        id = int(identities[i]) if identities is not None else 0

        # create new buffer for new object
        if id not in data_deque:  
          data_deque[id] = deque(maxlen= opt.trailslen)
          dtime[id] = datetime.datetime.now()
          dwell_time[id]=0
        else:
          curr_time = datetime.datetime.now()
          old_time = dtime[id]
          time_diff = curr_time - old_time
          dtime[id] = datetime.datetime.now()
          sec = time_diff.total_seconds()
          dwell_time[id] += sec

        text = "{}|{}".format(id, int(dwell_time[id]))
        print(text)
        cv2.putText(img, text, (x1, y1-5), cv2.FONT_HERSHEY_COMPLEX, 1, (0, 0, 255), 1)



        color = compute_color_for_labels(id)

        # add center to buffer
        data_deque[id].appendleft(center)

        # print(data_deque[id])

        # draw trail
        for i in range(1, len(data_deque[id])):
            # check if on buffer value is none
            if data_deque[id][i - 1] is None or data_deque[id][i] is None:
                continue

            # generate dynamic thickness of trails
            thickness = int(np.sqrt(opt.trailslen / float(i + i)) * 1.5)
            
            # draw trails
            cv2.line(img, data_deque[id][i - 1], data_deque[id][i], color, thickness)


        # box text and bar
        label = '{}{:d}'.format("", id)
        t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2, 2)[0]
        cv2.rectangle(img, (x1, y1), (x2, y2), color, 3)
        cv2.rectangle(
            img, (x1, y1), (x1 + t_size[0] + 3, y1 + t_size[1] + 4), color, -1)
        cv2.putText(img, label, (x1, y1 +
                                 t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 2, [255, 255, 255], 2)
    return img

def load_classes(path):
    # Loads *.names file at 'path'
    with open(path, 'r') as f:
        names = f.read().split('\n')
    return list(filter(None, names))  # filter removes empty strings (such as last line)

def detect(save_img=False):
    out, source, weights, view_img, save_txt, imgsz, cfg, names = \
        opt.output, opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size, opt.cfg, opt.names
    webcam = source == '0' or source.startswith('rtsp') or source.startswith('http') or source.endswith('.txt')

    # initialize deepsort
    cfg_deep = get_config()
    cfg_deep.merge_from_file("deep_sort_pytorch/configs/deep_sort.yaml")
    # attempt_download("deep_sort_pytorch/deep_sort/deep/checkpoint/ckpt.t7", repo='mikel-brostrom/Yolov5_DeepSort_Pytorch')
    deepsort = DeepSort(cfg_deep.DEEPSORT.REID_CKPT,
                        max_dist=cfg_deep.DEEPSORT.MAX_DIST, min_confidence=cfg_deep.DEEPSORT.MIN_CONFIDENCE,
                        nms_max_overlap=cfg_deep.DEEPSORT.NMS_MAX_OVERLAP, max_iou_distance=cfg_deep.DEEPSORT.MAX_IOU_DISTANCE,
                        max_age=cfg_deep.DEEPSORT.MAX_AGE, n_init=cfg_deep.DEEPSORT.N_INIT, nn_budget=cfg_deep.DEEPSORT.NN_BUDGET,
                        use_cuda=True)


    # Initialize
    device = select_device(opt.device)
    if os.path.exists(out):
        shutil.rmtree(out)  # delete output folder
    os.makedirs(out)  # make new output folder
    half = device.type != 'cpu'  # half precision only supported on CUDA

    # Load model
    model = Darknet(cfg, imgsz).cuda()
    model.load_state_dict(torch.load(weights[0], map_location=device)['model'])
    #model = attempt_load(weights, map_location=device)  # load FP32 model
    #imgsz = check_img_size(imgsz, s=model.stride.max())  # check img_size
    model.to(device).eval()
    if half:
        model.half()  # to FP16

    # Second-stage classifier
    classify = False
    if classify:
        modelc = load_classifier(name='resnet101', n=2)  # initialize
        modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model'])  # load weights
        modelc.to(device).eval()

    # Set Dataloader
    vid_path, vid_writer = None, None
    if webcam:
        view_img = True
        cudnn.benchmark = True  # set True to speed up constant image size inference
        dataset = LoadStreams(source, img_size=imgsz)
    else:
        save_img = True
        dataset = LoadImages(source, img_size=imgsz, auto_size=64)

    # Get names and colors
    names = load_classes(names)
    colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(names))]

    # Run inference
    t0 = time.time()
    img = torch.zeros((1, 3, imgsz, imgsz), device=device)  # init img
    _ = model(img.half() if half else img) if device.type != 'cpu' else None  # run once
    for path, img, im0s, vid_cap in dataset:
        img = torch.from_numpy(img).to(device)
        img = img.half() if half else img.float()  # uint8 to fp16/32
        img /= 255.0  # 0 - 255 to 0.0 - 1.0
        if img.ndimension() == 3:
            img = img.unsqueeze(0)

        # Inference
        t1 = time_synchronized()
        pred = model(img, augment=opt.augment)[0]

        # Apply NMS
        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
        t2 = time_synchronized()

        # Apply Classifier
        if classify:
            pred = apply_classifier(pred, modelc, img, im0s)

        # Process detections
        for i, det in enumerate(pred):  # detections per image
            if webcam:  # batch_size >= 1
                p, s, im0 = path[i], '%g: ' % i, im0s[i].copy()
            else:
                p, s, im0 = path, '', im0s

            save_path = str(Path(out) / Path(p).name)
            txt_path = str(Path(out) / Path(p).stem) + ('_%g' % dataset.frame if dataset.mode == 'video' else '')
            s += '%gx%g ' % img.shape[2:]  # print string
            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
            if det is not None and len(det):
                # Rescale boxes from img_size to im0 size
                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()

                # Print results
                for c in det[:, -1].unique():
                    n = (det[:, -1] == c).sum()  # detections per class
                    s += '%g %ss, ' % (n, names[int(c)])  # add to string

                xywh_bboxs = []
                confs = []

                # Write results
                for *xyxy, conf, cls in det:
                    # to deep sort format
                    x_c, y_c, bbox_w, bbox_h = xyxy_to_xywh(*xyxy)
                    xywh_obj = [x_c, y_c, bbox_w, bbox_h]
                    xywh_bboxs.append(xywh_obj)
                    confs.append([conf.item()])

                    if save_txt:  # Write to file
                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
                        with open(txt_path + '.txt', 'a') as f:
                            f.write(('%g ' * 5 + '\n') % (cls, *xywh))  # label format

                    # if save_img or view_img:  # Add bbox to image
                    #     label = '%s %.2f' % (names[int(cls)], conf)
                    #     plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3)

                xywhs = torch.Tensor(xywh_bboxs)
                confss = torch.Tensor(confs)

                outputs = deepsort.update(xywhs, confss, im0)
                if len(outputs) > 0:
                    bbox_xyxy = outputs[:, :4]
                    identities = outputs[:, -1]
                    draw_boxes(im0, bbox_xyxy, identities)


            # Print time (inference + NMS)
            print('%sDone. (%.3fs)' % (s, t2 - t1))

            # Stream results
            if view_img:
                cv2.imshow(p, im0)
                if cv2.waitKey(1) == ord('q'):  # q to quit
                    raise StopIteration

            # Save results (image with detections)
            if save_img:
                if dataset.mode == 'images':
                    cv2.imwrite(save_path, im0)
                else:
                    if vid_path != save_path:  # new video
                        vid_path = save_path
                        if isinstance(vid_writer, cv2.VideoWriter):
                            vid_writer.release()  # release previous video writer

                        fourcc = 'mp4v'  # output video codec
                        fps = vid_cap.get(cv2.CAP_PROP_FPS)
                        w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
                        h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
                        vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (w, h))
                    vid_writer.write(im0)

    if save_txt or save_img:
        print('Results saved to %s' % Path(out))
        if platform == 'darwin' and not opt.update:  # MacOS
            os.system('open ' + save_path)

    print('Done. (%.3fs)' % (time.time() - t0))


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default='yolor_p6.pt', help='model.pt path(s)')
    parser.add_argument('--source', type=str, default='inference/images', help='source')  # file/folder, 0 for webcam
    parser.add_argument('--output', type=str, default='inference/output', help='output folder')  # output folder
    parser.add_argument('--img-size', type=int, default=1280, help='inference size (pixels)')
    parser.add_argument('--conf-thres', type=float, default=0.4, help='object confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.5, help='IOU threshold for NMS')
    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--view-img', action='store_true', help='display results')
    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
    parser.add_argument('--augment', action='store_true', help='augmented inference')
    parser.add_argument('--update', action='store_true', help='update all models')
    parser.add_argument('--cfg', type=str, default='cfg/yolor_p6.cfg', help='*.cfg path')
    parser.add_argument('--names', type=str, default='data/coco.names', help='*.cfg path')
    parser.add_argument('--trailslen', type=int, default=64, help='trails size (new parameter)')
        
    opt = parser.parse_args()
    print(opt)

    with torch.no_grad():
        if opt.update:  # update all models (to fix SourceChangeWarning)
            for opt.weights in ['']:
                detect()
                strip_optimizer(opt.weights)
        else:
            detect()