目标检测初体验（一）

绝地灬酷狼 2023-03-13 05:56 127阅读 0赞

很久没有写CV方面的文章了，最近笔者接触了一段时间的目标检测的工具：darknet，因此希望能写篇文章记录下，同时希望自己能在目标检测有更深一步的研究。  
  目标检测是计算机视觉和数字图像处理的一个热门方向，广泛应用于机器人导航、智能视频监控、工业检测、航空航天等诸多领域，通过计算机视觉减少对人力资本的消耗，具有重要的现实意义。目标检测即找出图像中所有感兴趣的物体，包含物体定位和物体分类两个子任务，同时确定物体的类别和位置。图像分类的任务我们已经熟悉了，而目标检测与图片分类的不同之处在于，目标检测需要检测出图片中我们感兴趣的物体，同时检测出其边界并给出类别。  
  目前主流的目标检测算法主要是基于深度学习模型，大概可以分成两大类别：

1.  One-Stage目标检测算法，这类检测算法不需要产生候选区域(Region Proposal)阶段，可以通过一个Stage直接产生物体的类别概率和位置坐标值，比较典型的算法有YOLO、SSD和CornerNet；
2.  Two-Stage目标检测算法，这类检测算法将检测问题划分为两个阶段，第一个阶段首先产生候选区域，包含目标大概的位置信息，然后第二个阶段对候选区域进行分类和位置精修，这类算法的典型代表有R-CNN，Fast R-CNN，Faster R-CNN等。

目标检测模型的主要性能指标是检测准确度和速度，其中准确度主要考虑物体的定位以及分类准确度。一般情况下，Two-Stage算法在准确度上有优势，而One-Stage算法在速度上有优势。  
  darknet是一个开源的深度学习框架，它实现了YOLO算法，官方网站地址为：[https://pjreddie.com/darknet/yolo/][https_pjreddie.com_darknet_yolo]。基于它，我们能够很多有意思的事情。本文的后续部分将会给出darknet在图片和视频中进行目标检测的例子。

### 图像中的目标检测 ###

这部分将会给出darknet在图片中进行目标检测的例子。  
  首先我们先把darknet的源码下载到本地：

git clone https://github.com/pjreddie/darknet.git

然后我们下载已经预先训练好的YOLO3算法的模型`yolov3`，下载网址为：[https://pjreddie.com/media/files/yolov3.weights][https_pjreddie.com_media_files_yolov3.weights]，下载文件放在backup文件夹下。注意，该模型是在COCO数据集上训练的结果，COCO数据集包含80个类别，比如人、狗、车、猫等。  
  接着我们需要输入`make`命令进行编译，这会生成darnet可执行文件。  
  接着我们在网上找一张图片，对这张图片（位于data文件夹下的dog\_person.jpeg）进行目标检测，输入命令如下：

./darknet detect cfg/yolov3.cfg backup/yolov3.weights data/dog_person.jpeg

在本地的本地环境（CPU）中，输出结果如下：

Loading weights from backup/yolov3.weights...Done!
    data/dog_person.jpeg: Predicted in 19.373125 seconds.
    person: 96%
    person: 91%
    person: 87%
    person: 100%
    person: 100%
    person: 99%
    person: 99%
    dog: 100%

同时，也是生成一张预测图片predictions.jpg，内容如下：  
![示例图片][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2pjbGlhbjkx_size_16_color_FFFFFF_t_70_pic_center]  
虽然漏了其中的一条狗，但丝毫不影响该模型出色的目标检测的能力！这个结果对于初次接触目标检测的我是如此地让人兴奋！

### 视频中的目标检测 ###

接着是更为令人兴奋的部分。我们将在视频中进行目标检测。  
  由于笔者初次接触darknet，对很多内容还不是很熟悉，因此，借鉴别人已经写好的代码进行视频中的目标检测。  
  Python代码(detect\_video.py)如下：

# import the necessary packages
    import numpy as np
    import argparse
    import imutils
    import time
    import cv2
    import os
    
    # construct the argument parse and parse the arguments
    ap = argparse.ArgumentParser()
    ap.add_argument("-i", "--input", required=True,
        help="path to input video")
    ap.add_argument("-o", "--output", required=True,
        help="path to output video")
    ap.add_argument("-y", "--yolo", required=True,
        help="base path to YOLO directory")
    ap.add_argument("-c", "--confidence", type=float, default=0.5,
        help="minimum probability to filter weak detections")
    ap.add_argument("-t", "--threshold", type=float, default=0.3,
        help="threshold when applyong non-maxima suppression")
    args = vars(ap.parse_args())
    
    # load the COCO class labels our YOLO model was trained on
    labelsPath = os.path.sep.join([args["yolo"], "coco.names"])
    LABELS = open(labelsPath).read().strip().split("\n")
    # initialize a list of colors to represent each possible class label
    np.random.seed(42)
    COLORS = np.random.randint(0, 255, size=(len(LABELS), 3), dtype="uint8")
    # derive the paths to the YOLO weights and model configuration
    weightsPath = os.path.sep.join([args["yolo"], "yolov3.weights"])
    configPath = os.path.sep.join([args["yolo"], "yolov3.cfg"])
    # load our YOLO object detector trained on COCO dataset (80 classes)
    # and determine only the *output* layer names that we need from YOLO
    print("[INFO] loading YOLO from disk...")
    net = cv2.dnn.readNetFromDarknet(configPath, weightsPath)
    ln = net.getLayerNames()
    ln = [ln[i[0] - 1] for i in net.getUnconnectedOutLayers()]
    
    # initialize the video stream, pointer to output video file, and
    # frame dimensions
    vs = cv2.VideoCapture(args["input"])
    writer = None
    (W, H) = (None, None)
    # try to determine the total number of frames in the video file
    try:
        prop = cv2.cv.CV_CAP_PROP_FRAME_COUNT if imutils.is_cv2() \
            else cv2.CAP_PROP_FRAME_COUNT
        total = int(vs.get(prop))
        print("[INFO] {} total frames in video".format(total))
    # an error occurred while trying to determine the total
    # number of frames in the video file
    except Exception:
        print("[INFO] could not determine # of frames in video")
        print("[INFO] no approx. completion time can be provided")
        total = -1
    
    # loop over frames from the video file stream
    while True:
        # read the next frame from the file
        (grabbed, frame) = vs.read()
        # if the frame was not grabbed, then we have reached the end
        # of the stream
        if not grabbed:
            break
        # if the frame dimensions are empty, grab them
        if W is None or H is None:
            (H, W) = frame.shape[:2]
    
        # construct a blob from the input frame and then perform a forward
        # pass of the YOLO object detector, giving us our bounding boxes
        # and associated probabilities
        blob = cv2.dnn.blobFromImage(frame, 1 / 255.0, (416, 416), swapRB=True, crop=False)
        net.setInput(blob)
        start = time.time()
        layerOutputs = net.forward(ln)
        end = time.time()
        # initialize our lists of detected bounding boxes, confidences,
        # and class IDs, respectively
        boxes = []
        confidences = []
        classIDs = []
    
        # loop over each of the layer outputs
        for output in layerOutputs:
            # loop over each of the detections
            for detection in output:
                # extract the class ID and confidence (i.e., probability)
                # of the current object detection
                scores = detection[5:]
                classID = np.argmax(scores)
                confidence = scores[classID]
                # filter out weak predictions by ensuring the detected
                # probability is greater than the minimum probability
                if confidence > args["confidence"]:
                    # scale the bounding box coordinates back relative to
                    # the size of the image, keeping in mind that YOLO
                    # actually returns the center (x, y)-coordinates of
                    # the bounding box followed by the boxes' width and
                    # height
                    box = detection[0:4] * np.array([W, H, W, H])
                    (centerX, centerY, width, height) = box.astype("int")
                    # use the center (x, y)-coordinates to derive the top
                    # and and left corner of the bounding box
                    x = int(centerX - (width / 2))
                    y = int(centerY - (height / 2))
                    # update our list of bounding box coordinates,
                    # confidences, and class IDs
                    boxes.append([x, y, int(width), int(height)])
                    confidences.append(float(confidence))
                    classIDs.append(classID)
    
        # apply non-maxima suppression to suppress weak, overlapping
        # bounding boxes
        idxs = cv2.dnn.NMSBoxes(boxes, confidences, args["confidence"], args["threshold"])
        # ensure at least one detection exists
        if len(idxs) > 0:
            # loop over the indexes we are keeping
            for i in idxs.flatten():
                # extract the bounding box coordinates
                (x, y) = (boxes[i][0], boxes[i][1])
                (w, h) = (boxes[i][2], boxes[i][3])
                # draw a bounding box rectangle and label on the frame
                color = [int(c) for c in COLORS[classIDs[i]]]
                cv2.rectangle(frame, (x, y), (x + w, y + h), color, 2)
                text = "{}: {:.4f}".format(LABELS[classIDs[i]], confidences[i])
                cv2.putText(frame, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
    
        # check if the video writer is None
        if writer is None:
            # initialize our video writer
            fourcc = cv2.VideoWriter_fourcc(*"MJPG")
            writer = cv2.VideoWriter(args["output"], fourcc, 30, (frame.shape[1], frame.shape[0]), True)
            # some information on processing single frame
            if total > 0:
                elap = (end - start)
                print("[INFO] single frame took {:.4f} seconds".format(elap))
                print("[INFO] estimated total time to finish: {:.4f}".format(elap * total))
        # write the output frame to disk
        writer.write(frame)
    # release the file pointers
    print("[INFO] cleaning up...")
    writer.release()
    vs.release()

我们把coco.names和yolov3.cfg文件都放在backup文件夹下。然后，我们再输入下面的命令（注意：jishengchong.mp4为输入视频文件，位于data文件夹下，jishengchong.avi为输出文件，里面包含目标检测的结果）：

python3 detect_video.py --input ../data/jishengchong.mp4 --output ../data/jishengchong.avi --yolo ../backup

由于视频检测太费时间，因此，我在这里只给出该视频的前10秒的检测结果，如下：

可以参考微信公众号上的文章：[https://mp.weixin.qq.com/s?\_\_biz=MzU2NTYyMDk5MQ==&mid=2247484606&idx=1&sn=52862414c7689b53a58941651f7f49a0&chksm=fcb9bd2ecbce34385b92d32625c819ce28f0e41af2eaf4a6df38cfb71651bdb293e4c4cfeb5f&token=679045967&lang=zh\_CN\#rd][https_mp.weixin.qq.com_s_biz_MzU2NTYyMDk5MQ_mid_2247484606_idx_1_sn_52862414c7689b53a58941651f7f49a0_chksm_fcb9bd2ecbce34385b92d32625c819ce28f0e41af2eaf4a6df38cfb71651bdb293e4c4cfeb5f_token_679045967_lang_zh_CN_rd] 。

### 总结 ###

本次作为笔者入门目标检测的第一篇文章，希望以后也能在这个方向又一定深度的研究。

[https_pjreddie.com_darknet_yolo]: https://pjreddie.com/darknet/yolo/
[https_pjreddie.com_media_files_yolov3.weights]: https://pjreddie.com/media/files/yolov3.weights
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2pjbGlhbjkx_size_16_color_FFFFFF_t_70_pic_center]: /images/20230312/152ef52f9fdb41be98ae9bab3dcc7c79.png
[https_mp.weixin.qq.com_s_biz_MzU2NTYyMDk5MQ_mid_2247484606_idx_1_sn_52862414c7689b53a58941651f7f49a0_chksm_fcb9bd2ecbce34385b92d32625c819ce28f0e41af2eaf4a6df38cfb71651bdb293e4c4cfeb5f_token_679045967_lang_zh_CN_rd]: https://mp.weixin.qq.com/s?__biz=MzU2NTYyMDk5MQ==&mid=2247484606&idx=1&sn=52862414c7689b53a58941651f7f49a0&chksm=fcb9bd2ecbce34385b92d32625c819ce28f0e41af2eaf4a6df38cfb71651bdb293e4c4cfeb5f&token=679045967&lang=zh_CN#rd