Upload 8 files

deep_sort/utils/asserts.py

@@ -0,0 +1,13 @@
+from os import environ
+
+
+def assert_in(file, files_to_check):
+    if file not in files_to_check:
+        raise AssertionError("{} does not exist in the list".format(str(file)))
+    return True
+
+
+def assert_in_env(check_list: list):
+    for item in check_list:
+        assert_in(item, environ.keys())
+    return True

deep_sort/utils/draw.py

@@ -0,0 +1,36 @@
+import numpy as np
+import cv2
+
+palette = (2 ** 11 - 1, 2 ** 15 - 1, 2 ** 20 - 1)
+
+
+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)):
+    for i,box in enumerate(bbox):
+        x1,y1,x2,y2 = [int(i) for i in box]
+        x1 += offset[0]
+        x2 += offset[0]
+        y1 += offset[1]
+        y2 += offset[1]
+        # box text and bar
+        id = int(identities[i]) if identities is not None else 0    
+        color = compute_color_for_labels(id)
+        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
+
+
+
+if __name__ == '__main__':
+    for i in range(82):
+        print(compute_color_for_labels(i))

deep_sort/utils/evaluation.py

@@ -0,0 +1,103 @@
+import os
+import numpy as np
+import copy
+import motmetrics as mm
+mm.lap.default_solver = 'lap'
+from utils.io import read_results, unzip_objs
+
+
+class Evaluator(object):
+
+    def __init__(self, data_root, seq_name, data_type):
+        self.data_root = data_root
+        self.seq_name = seq_name
+        self.data_type = data_type
+
+        self.load_annotations()
+        self.reset_accumulator()
+
+    def load_annotations(self):
+        assert self.data_type == 'mot'
+
+        gt_filename = os.path.join(self.data_root, self.seq_name, 'gt', 'gt.txt')
+        self.gt_frame_dict = read_results(gt_filename, self.data_type, is_gt=True)
+        self.gt_ignore_frame_dict = read_results(gt_filename, self.data_type, is_ignore=True)
+
+    def reset_accumulator(self):
+        self.acc = mm.MOTAccumulator(auto_id=True)
+
+    def eval_frame(self, frame_id, trk_tlwhs, trk_ids, rtn_events=False):
+        # results
+        trk_tlwhs = np.copy(trk_tlwhs)
+        trk_ids = np.copy(trk_ids)
+
+        # gts
+        gt_objs = self.gt_frame_dict.get(frame_id, [])
+        gt_tlwhs, gt_ids = unzip_objs(gt_objs)[:2]
+
+        # ignore boxes
+        ignore_objs = self.gt_ignore_frame_dict.get(frame_id, [])
+        ignore_tlwhs = unzip_objs(ignore_objs)[0]
+
+
+        # remove ignored results
+        keep = np.ones(len(trk_tlwhs), dtype=bool)
+        iou_distance = mm.distances.iou_matrix(ignore_tlwhs, trk_tlwhs, max_iou=0.5)
+        if len(iou_distance) > 0:
+            match_is, match_js = mm.lap.linear_sum_assignment(iou_distance)
+            match_is, match_js = map(lambda a: np.asarray(a, dtype=int), [match_is, match_js])
+            match_ious = iou_distance[match_is, match_js]
+
+            match_js = np.asarray(match_js, dtype=int)
+            match_js = match_js[np.logical_not(np.isnan(match_ious))]
+            keep[match_js] = False
+            trk_tlwhs = trk_tlwhs[keep]
+            trk_ids = trk_ids[keep]
+
+        # get distance matrix
+        iou_distance = mm.distances.iou_matrix(gt_tlwhs, trk_tlwhs, max_iou=0.5)
+
+        # acc
+        self.acc.update(gt_ids, trk_ids, iou_distance)
+
+        if rtn_events and iou_distance.size > 0 and hasattr(self.acc, 'last_mot_events'):
+            events = self.acc.last_mot_events  # only supported by https://github.com/longcw/py-motmetrics
+        else:
+            events = None
+        return events
+
+    def eval_file(self, filename):
+        self.reset_accumulator()
+
+        result_frame_dict = read_results(filename, self.data_type, is_gt=False)
+        frames = sorted(list(set(self.gt_frame_dict.keys()) | set(result_frame_dict.keys())))
+        for frame_id in frames:
+            trk_objs = result_frame_dict.get(frame_id, [])
+            trk_tlwhs, trk_ids = unzip_objs(trk_objs)[:2]
+            self.eval_frame(frame_id, trk_tlwhs, trk_ids, rtn_events=False)
+
+        return self.acc
+
+    @staticmethod
+    def get_summary(accs, names, metrics=('mota', 'num_switches', 'idp', 'idr', 'idf1', 'precision', 'recall')):
+        names = copy.deepcopy(names)
+        if metrics is None:
+            metrics = mm.metrics.motchallenge_metrics
+        metrics = copy.deepcopy(metrics)
+
+        mh = mm.metrics.create()
+        summary = mh.compute_many(
+            accs,
+            metrics=metrics,
+            names=names,
+            generate_overall=True
+        )
+
+        return summary
+
+    @staticmethod
+    def save_summary(summary, filename):
+        import pandas as pd
+        writer = pd.ExcelWriter(filename)
+        summary.to_excel(writer)
+        writer.save()

deep_sort/utils/io.py

@@ -0,0 +1,133 @@
+import os
+from typing import Dict
+import numpy as np
+
+# from utils.log import get_logger
+
+
+def write_results(filename, results, data_type):
+    if data_type == 'mot':
+        save_format = '{frame},{id},{x1},{y1},{w},{h},-1,-1,-1,-1\n'
+    elif data_type == 'kitti':
+        save_format = '{frame} {id} pedestrian 0 0 -10 {x1} {y1} {x2} {y2} -10 -10 -10 -1000 -1000 -1000 -10\n'
+    else:
+        raise ValueError(data_type)
+
+    with open(filename, 'w') as f:
+        for frame_id, tlwhs, track_ids in results:
+            if data_type == 'kitti':
+                frame_id -= 1
+            for tlwh, track_id in zip(tlwhs, track_ids):
+                if track_id < 0:
+                    continue
+                x1, y1, w, h = tlwh
+                x2, y2 = x1 + w, y1 + h
+                line = save_format.format(frame=frame_id, id=track_id, x1=x1, y1=y1, x2=x2, y2=y2, w=w, h=h)
+                f.write(line)
+
+
+# def write_results(filename, results_dict: Dict, data_type: str):
+#     if not filename:
+#         return
+#     path = os.path.dirname(filename)
+#     if not os.path.exists(path):
+#         os.makedirs(path)
+
+#     if data_type in ('mot', 'mcmot', 'lab'):
+#         save_format = '{frame},{id},{x1},{y1},{w},{h},1,-1,-1,-1\n'
+#     elif data_type == 'kitti':
+#         save_format = '{frame} {id} pedestrian -1 -1 -10 {x1} {y1} {x2} {y2} -1 -1 -1 -1000 -1000 -1000 -10 {score}\n'
+#     else:
+#         raise ValueError(data_type)
+
+#     with open(filename, 'w') as f:
+#         for frame_id, frame_data in results_dict.items():
+#             if data_type == 'kitti':
+#                 frame_id -= 1
+#             for tlwh, track_id in frame_data:
+#                 if track_id < 0:
+#                     continue
+#                 x1, y1, w, h = tlwh
+#                 x2, y2 = x1 + w, y1 + h
+#                 line = save_format.format(frame=frame_id, id=track_id, x1=x1, y1=y1, x2=x2, y2=y2, w=w, h=h, score=1.0)
+#                 f.write(line)
+#     logger.info('Save results to {}'.format(filename))
+
+
+def read_results(filename, data_type: str, is_gt=False, is_ignore=False):
+    if data_type in ('mot', 'lab'):
+        read_fun = read_mot_results
+    else:
+        raise ValueError('Unknown data type: {}'.format(data_type))
+
+    return read_fun(filename, is_gt, is_ignore)
+
+
+"""
+labels={'ped', ...			% 1
+'person_on_vhcl', ...	% 2
+'car', ...				% 3
+'bicycle', ...			% 4
+'mbike', ...			% 5
+'non_mot_vhcl', ...		% 6
+'static_person', ...	% 7
+'distractor', ...		% 8
+'occluder', ...			% 9
+'occluder_on_grnd', ...		%10
+'occluder_full', ...		% 11
+'reflection', ...		% 12
+'crowd' ...			% 13
+};
+"""
+
+
+def read_mot_results(filename, is_gt, is_ignore):
+    valid_labels = {1}
+    ignore_labels = {2, 7, 8, 12}
+    results_dict = dict()
+    if os.path.isfile(filename):
+        with open(filename, 'r') as f:
+            for line in f.readlines():
+                linelist = line.split(',')
+                if len(linelist) < 7:
+                    continue
+                fid = int(linelist[0])
+                if fid < 1:
+                    continue
+                results_dict.setdefault(fid, list())
+
+                if is_gt:
+                    if 'MOT16-' in filename or 'MOT17-' in filename:
+                        label = int(float(linelist[7]))
+                        mark = int(float(linelist[6]))
+                        if mark == 0 or label not in valid_labels:
+                            continue
+                    score = 1
+                elif is_ignore:
+                    if 'MOT16-' in filename or 'MOT17-' in filename:
+                        label = int(float(linelist[7]))
+                        vis_ratio = float(linelist[8])
+                        if label not in ignore_labels and vis_ratio >= 0:
+                            continue
+                    else:
+                        continue
+                    score = 1
+                else:
+                    score = float(linelist[6])
+
+                tlwh = tuple(map(float, linelist[2:6]))
+                target_id = int(linelist[1])
+
+                results_dict[fid].append((tlwh, target_id, score))
+
+    return results_dict
+
+
+def unzip_objs(objs):
+    if len(objs) > 0:
+        tlwhs, ids, scores = zip(*objs)
+    else:
+        tlwhs, ids, scores = [], [], []
+    tlwhs = np.asarray(tlwhs, dtype=float).reshape(-1, 4)
+
+    return tlwhs, ids, scores

deep_sort/utils/json_logger.py

@@ -0,0 +1,383 @@
+"""
+References:
+    https://medium.com/analytics-vidhya/creating-a-custom-logging-mechanism-for-real-time-object-detection-using-tdd-4ca2cfcd0a2f
+"""
+import json
+from os import makedirs
+from os.path import exists, join
+from datetime import datetime
+
+
+class JsonMeta(object):
+    HOURS = 3
+    MINUTES = 59
+    SECONDS = 59
+    PATH_TO_SAVE = 'LOGS'
+    DEFAULT_FILE_NAME = 'remaining'
+
+
+class BaseJsonLogger(object):
+    """
+    This is the base class that returns __dict__ of its own
+    it also returns the dicts of objects in the attributes that are list instances
+
+    """
+
+    def dic(self):
+        # returns dicts of objects
+        out = {}
+        for k, v in self.__dict__.items():
+            if hasattr(v, 'dic'):
+                out[k] = v.dic()
+            elif isinstance(v, list):
+                out[k] = self.list(v)
+            else:
+                out[k] = v
+        return out
+
+    @staticmethod
+    def list(values):
+        # applies the dic method on items in the list
+        return [v.dic() if hasattr(v, 'dic') else v for v in values]
+
+
+class Label(BaseJsonLogger):
+    """
+    For each bounding box there are various categories with confidences. Label class keeps track of that information.
+    """
+
+    def __init__(self, category: str, confidence: float):
+        self.category = category
+        self.confidence = confidence
+
+
+class Bbox(BaseJsonLogger):
+    """
+    This module stores the information for each frame and use them in JsonParser
+    Attributes:
+        labels (list): List of label module.
+        top (int):
+        left (int):
+        width (int):
+        height (int):
+
+    Args:
+        bbox_id (float):
+        top (int):
+        left (int):
+        width (int):
+        height (int):
+
+    References:
+        Check Label module for better understanding.
+
+
+    """
+
+    def __init__(self, bbox_id, top, left, width, height):
+        self.labels = []
+        self.bbox_id = bbox_id
+        self.top = top
+        self.left = left
+        self.width = width
+        self.height = height
+
+    def add_label(self, category, confidence):
+        # adds category and confidence only if top_k is not exceeded.
+        self.labels.append(Label(category, confidence))
+
+    def labels_full(self, value):
+        return len(self.labels) == value
+
+
+class Frame(BaseJsonLogger):
+    """
+    This module stores the information for each frame and use them in JsonParser
+    Attributes:
+        timestamp (float): The elapsed time of captured frame
+        frame_id (int): The frame number of the captured video
+        bboxes (list of Bbox objects): Stores the list of bbox objects.
+
+    References:
+        Check Bbox class for better information
+
+    Args:
+        timestamp (float):
+        frame_id (int):
+
+    """
+
+    def __init__(self, frame_id: int, timestamp: float = None):
+        self.frame_id = frame_id
+        self.timestamp = timestamp
+        self.bboxes = []
+
+    def add_bbox(self, bbox_id: int, top: int, left: int, width: int, height: int):
+        bboxes_ids = [bbox.bbox_id for bbox in self.bboxes]
+        if bbox_id not in bboxes_ids:
+            self.bboxes.append(Bbox(bbox_id, top, left, width, height))
+        else:
+            raise ValueError("Frame with id: {} already has a Bbox with id: {}".format(self.frame_id, bbox_id))
+
+    def add_label_to_bbox(self, bbox_id: int, category: str, confidence: float):
+        bboxes = {bbox.id: bbox for bbox in self.bboxes}
+        if bbox_id in bboxes.keys():
+            res = bboxes.get(bbox_id)
+            res.add_label(category, confidence)
+        else:
+            raise ValueError('the bbox with id: {} does not exists!'.format(bbox_id))
+
+
+class BboxToJsonLogger(BaseJsonLogger):
+    """
+    ُ This module is designed to automate the task of logging jsons. An example json is used
+    to show the contents of json file shortly
+    Example:
+          {
+          "video_details": {
+            "frame_width": 1920,
+            "frame_height": 1080,
+            "frame_rate": 20,
+            "video_name": "/home/gpu/codes/MSD/pedestrian_2/project/public/camera1.avi"
+          },
+          "frames": [
+            {
+              "frame_id": 329,
+              "timestamp": 3365.1254
+              "bboxes": [
+                {
+                  "labels": [
+                    {
+                      "category": "pedestrian",
+                      "confidence": 0.9
+                    }
+                  ],
+                  "bbox_id": 0,
+                  "top": 1257,
+                  "left": 138,
+                  "width": 68,
+                  "height": 109
+                }
+              ]
+            }],
+
+    Attributes:
+        frames (dict): It's a dictionary that maps each frame_id to json attributes.
+        video_details (dict): information about video file.
+        top_k_labels (int): shows the allowed number of labels
+        start_time (datetime object): we use it to automate the json output by time.
+
+    Args:
+        top_k_labels (int): shows the allowed number of labels
+
+    """
+
+    def __init__(self, top_k_labels: int = 1):
+        self.frames = {}
+        self.video_details = self.video_details = dict(frame_width=None, frame_height=None, frame_rate=None,
+                                                       video_name=None)
+        self.top_k_labels = top_k_labels
+        self.start_time = datetime.now()
+
+    def set_top_k(self, value):
+        self.top_k_labels = value
+
+    def frame_exists(self, frame_id: int) -> bool:
+        """
+        Args:
+            frame_id (int):
+
+        Returns:
+            bool: true if frame_id is recognized
+        """
+        return frame_id in self.frames.keys()
+
+    def add_frame(self, frame_id: int, timestamp: float = None) -> None:
+        """
+        Args:
+            frame_id (int):
+            timestamp (float): opencv captured frame time property
+
+        Raises:
+             ValueError: if frame_id would not exist in class frames attribute
+
+        Returns:
+            None
+
+        """
+        if not self.frame_exists(frame_id):
+            self.frames[frame_id] = Frame(frame_id, timestamp)
+        else:
+            raise ValueError("Frame id: {} already exists".format(frame_id))
+
+    def bbox_exists(self, frame_id: int, bbox_id: int) -> bool:
+        """
+        Args:
+            frame_id:
+            bbox_id:
+
+        Returns:
+            bool: if bbox exists in frame bboxes list
+        """
+        bboxes = []
+        if self.frame_exists(frame_id=frame_id):
+            bboxes = [bbox.bbox_id for bbox in self.frames[frame_id].bboxes]
+        return bbox_id in bboxes
+
+    def find_bbox(self, frame_id: int, bbox_id: int):
+        """
+
+        Args:
+            frame_id:
+            bbox_id:
+
+        Returns:
+            bbox_id (int):
+
+        Raises:
+            ValueError: if bbox_id does not exist in the bbox list of specific frame.
+        """
+        if not self.bbox_exists(frame_id, bbox_id):
+            raise ValueError("frame with id: {} does not contain bbox with id: {}".format(frame_id, bbox_id))
+        bboxes = {bbox.bbox_id: bbox for bbox in self.frames[frame_id].bboxes}
+        return bboxes.get(bbox_id)
+
+    def add_bbox_to_frame(self, frame_id: int, bbox_id: int, top: int, left: int, width: int, height: int) -> None:
+        """
+
+        Args:
+            frame_id (int):
+            bbox_id (int):
+            top (int):
+            left (int):
+            width (int):
+            height (int):
+
+        Returns:
+            None
+
+        Raises:
+            ValueError: if bbox_id already exist in frame information with frame_id
+            ValueError: if frame_id does not exist in frames attribute
+        """
+        if self.frame_exists(frame_id):
+            frame = self.frames[frame_id]
+            if not self.bbox_exists(frame_id, bbox_id):
+                frame.add_bbox(bbox_id, top, left, width, height)
+            else:
+                raise ValueError(
+                    "frame with frame_id: {} already contains the bbox with id: {} ".format(frame_id, bbox_id))
+        else:
+            raise ValueError("frame with frame_id: {} does not exist".format(frame_id))
+
+    def add_label_to_bbox(self, frame_id: int, bbox_id: int, category: str, confidence: float):
+        """
+        Args:
+            frame_id:
+            bbox_id:
+            category:
+            confidence: the confidence value returned from yolo detection
+
+        Returns:
+            None
+
+        Raises:
+            ValueError: if labels quota (top_k_labels) exceeds.
+        """
+        bbox = self.find_bbox(frame_id, bbox_id)
+        if not bbox.labels_full(self.top_k_labels):
+            bbox.add_label(category, confidence)
+        else:
+            raise ValueError("labels in frame_id: {}, bbox_id: {} is fulled".format(frame_id, bbox_id))
+
+    def add_video_details(self, frame_width: int = None, frame_height: int = None, frame_rate: int = None,
+                          video_name: str = None):
+        self.video_details['frame_width'] = frame_width
+        self.video_details['frame_height'] = frame_height
+        self.video_details['frame_rate'] = frame_rate
+        self.video_details['video_name'] = video_name
+
+    def output(self):
+        output = {'video_details': self.video_details}
+        result = list(self.frames.values())
+        output['frames'] = [item.dic() for item in result]
+        return output
+
+    def json_output(self, output_name):
+        """
+        Args:
+            output_name:
+
+        Returns:
+            None
+
+        Notes:
+            It creates the json output with `output_name` name.
+        """
+        if not output_name.endswith('.json'):
+            output_name += '.json'
+        with open(output_name, 'w') as file:
+            json.dump(self.output(), file)
+        file.close()
+
+    def set_start(self):
+        self.start_time = datetime.now()
+
+    def schedule_output_by_time(self, output_dir=JsonMeta.PATH_TO_SAVE, hours: int = 0, minutes: int = 0,
+                                seconds: int = 60) -> None:
+        """
+        Notes:
+            Creates folder and then periodically stores the jsons on that address.
+
+        Args:
+            output_dir (str): the directory where output files will be stored
+            hours (int):
+            minutes (int):
+            seconds (int):
+
+        Returns:
+            None
+
+        """
+        end = datetime.now()
+        interval = 0
+        interval += abs(min([hours, JsonMeta.HOURS]) * 3600)
+        interval += abs(min([minutes, JsonMeta.MINUTES]) * 60)
+        interval += abs(min([seconds, JsonMeta.SECONDS]))
+        diff = (end - self.start_time).seconds
+
+        if diff > interval:
+            output_name = self.start_time.strftime('%Y-%m-%d %H-%M-%S') + '.json'
+            if not exists(output_dir):
+                makedirs(output_dir)
+            output = join(output_dir, output_name)
+            self.json_output(output_name=output)
+            self.frames = {}
+            self.start_time = datetime.now()
+
+    def schedule_output_by_frames(self, frames_quota, frame_counter, output_dir=JsonMeta.PATH_TO_SAVE):
+        """
+        saves as the number of frames quota increases higher.
+        :param frames_quota:
+        :param frame_counter:
+        :param output_dir:
+        :return:
+        """
+        pass
+
+    def flush(self, output_dir):
+        """
+        Notes:
+            We use this function to output jsons whenever possible.
+            like the time that we exit the while loop of opencv.
+
+        Args:
+            output_dir:
+
+        Returns:
+            None
+
+        """
+        filename = self.start_time.strftime('%Y-%m-%d %H-%M-%S') + '-remaining.json'
+        output = join(output_dir, filename)
+        self.json_output(output_name=output)

deep_sort/utils/log.py

@@ -0,0 +1,17 @@
+import logging
+
+
+def get_logger(name='root'):
+    formatter = logging.Formatter(
+        # fmt='%(asctime)s [%(levelname)s]: %(filename)s(%(funcName)s:%(lineno)s) >> %(message)s')
+        fmt='%(asctime)s [%(levelname)s]: %(message)s', datefmt='%Y-%m-%d %H:%M:%S')
+
+    handler = logging.StreamHandler()
+    handler.setFormatter(formatter)
+
+    logger = logging.getLogger(name)
+    logger.setLevel(logging.INFO)
+    logger.addHandler(handler)
+    return logger
+
+

deep_sort/utils/tools.py

@@ -0,0 +1,39 @@
+from functools import wraps
+from time import time
+
+
+def is_video(ext: str):
+    """
+    Returns true if ext exists in
+    allowed_exts for video files.
+
+    Args:
+        ext:
+
+    Returns:
+
+    """
+
+    allowed_exts = ('.mp4', '.webm', '.ogg', '.avi', '.wmv', '.mkv', '.3gp')
+    return any((ext.endswith(x) for x in allowed_exts))
+
+
+def tik_tok(func):
+    """
+    keep track of time for each process.
+    Args:
+        func:
+
+    Returns:
+
+    """
+    @wraps(func)
+    def _time_it(*args, **kwargs):
+        start = time()
+        try:
+            return func(*args, **kwargs)
+        finally:
+            end_ = time()
+            print("time: {:.03f}s, fps: {:.03f}".format(end_ - start, 1 / (end_ - start)))
+
+    return _time_it