deep_sort_yolov3视频检测代码(可直接输入mp4格式,也可以是一帧帧的图片).rar

上传者: 42663696 | 上传时间: 2021-03-27 18:06:22 | 文件大小: 10.08MB | 文件类型: RAR
资源为视频检测算法代码包括算法的模型,算法实现的原理是:首先在视频检测跟踪之前,对所有目标已经完成检测,那么当第一帧进来时,以检测到的目标初始化并创建新的跟踪器,标注ID,输出行人图片,输出一组向量,通过比对两个向量之间的距离,来判断两副输入图片是否是同一个行人。在后面帧进来时,先到卡尔曼滤波器中得到由前面帧box产生的状态预测和协方差预测,并且使用确信度较高的跟踪结果进行预测结果的修正。求跟踪器所有目标状态与本帧检测的box的IOU,通过匈牙利算法寻找二分图的最大匹配,在多目标检测跟踪问题中为寻找前后两帧的若干目标的匹配最优解,得到IOU最大的唯一匹配,在去掉匹配值小于iou_threshold的匹配对。 用本帧中匹配到的目标检测box去更新卡尔曼跟踪器,计算卡尔曼增益,状态更新和协方差更新。并将状态更新值输出,作为本帧的跟踪box,再对于本帧中没有匹配到的目标重新初始化跟踪器。 yolo v3首先通过特征提取网络对输入图像提取特征,得到一定size的feature map,通过尺寸聚类确定anchor box。对每个bounding box网络预测4个坐标偏移。如果feature map某一单元偏移图片左上角坐标,bounding box预选框尺寸为,即anchor尺寸,那么生成对预测坐标为,此为feature map层级.而为真值在feature map上的映射,通过预测偏移使得与一致。类别预测方面为多标签分类,采用多个scale融合的方式做预测。

文件下载

资源详情

[{"title":"( 54 个子文件 10.08MB ) deep_sort_yolov3视频检测代码(可直接输入mp4格式,也可以是一帧帧的图片).rar","children":[{"title":"deep_sort_yolov3","children":[{"title":"yolo_tracking.py <span style='color:#111;'> 5.11KB </span>","children":null,"spread":false},{"title":"yolo3","children":[{"title":"utils.pyc <span style='color:#111;'> 1.62KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 976B </span>","children":null,"spread":false},{"title":"model.py <span style='color:#111;'> 13.54KB </span>","children":null,"spread":false},{"title":"__init__.pyc <span style='color:#111;'> 137B </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"model.cpython-35.pyc <span style='color:#111;'> 12.44KB </span>","children":null,"spread":false},{"title":"__init__.cpython-35.pyc <span style='color:#111;'> 145B </span>","children":null,"spread":false},{"title":"utils.cpython-35.pyc <span style='color:#111;'> 1.40KB </span>","children":null,"spread":false}],"spread":true},{"title":"model.pyc <span style='color:#111;'> 13.27KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"yolo.pyc <span style='color:#111;'> 5.12KB </span>","children":null,"spread":false},{"title":"convert.py <span style='color:#111;'> 9.53KB </span>","children":null,"spread":false},{"title":"yolo.py <span style='color:#111;'> 4.47KB </span>","children":null,"spread":false},{"title":"deep_sort","children":[{"title":"iou_matching.pyc <span style='color:#111;'> 3.12KB </span>","children":null,"spread":false},{"title":"nn_matching.pyc <span style='color:#111;'> 6.70KB </span>","children":null,"spread":false},{"title":"preprocessing.pyc <span style='color:#111;'> 2.13KB </span>","children":null,"spread":false},{"title":"kalman_filter.py <span style='color:#111;'> 7.60KB </span>","children":null,"spread":false},{"title":"nn_matching.py <span style='color:#111;'> 5.34KB </span>","children":null,"spread":false},{"title":"preprocessing.py <span style='color:#111;'> 1.87KB </span>","children":null,"spread":false},{"title":"tracker.pyc <span style='color:#111;'> 5.15KB </span>","children":null,"spread":false},{"title":"track.py <span style='color:#111;'> 4.86KB </span>","children":null,"spread":false},{"title":"track.pyc <span style='color:#111;'> 6.05KB </span>","children":null,"spread":false},{"title":"detection.py <span style='color:#111;'> 1.40KB </span>","children":null,"spread":false},{"title":"linear_assignment.pyc <span style='color:#111;'> 7.22KB </span>","children":null,"spread":false},{"title":"tracker.py <span style='color:#111;'> 5.17KB </span>","children":null,"spread":false},{"title":"detection.pyc <span style='color:#111;'> 2.08KB </span>","children":null,"spread":false},{"title":"__init__.pyc <span style='color:#111;'> 146B </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"__init__.cpython-35.pyc <span style='color:#111;'> 149B </span>","children":null,"spread":false},{"title":"detection.cpython-35.pyc <span style='color:#111;'> 1.87KB </span>","children":null,"spread":false},{"title":"tracker.cpython-35.pyc <span style='color:#111;'> 5.63KB </span>","children":null,"spread":false},{"title":"preprocessing.cpython-35.pyc <span style='color:#111;'> 1.98KB </span>","children":null,"spread":false},{"title":"iou_matching.cpython-35.pyc <span style='color:#111;'> 3.00KB </span>","children":null,"spread":false},{"title":"track.cpython-35.pyc <span style='color:#111;'> 5.50KB </span>","children":null,"spread":false},{"title":"kalman_filter.cpython-35.pyc <span style='color:#111;'> 6.88KB </span>","children":null,"spread":false},{"title":"nn_matching.cpython-35.pyc <span style='color:#111;'> 6.16KB </span>","children":null,"spread":false},{"title":"linear_assignment.cpython-35.pyc <span style='color:#111;'> 7.05KB </span>","children":null,"spread":false}],"spread":false},{"title":"linear_assignment.py <span style='color:#111;'> 7.60KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 27B </span>","children":null,"spread":false},{"title":"iou_matching.py <span style='color:#111;'> 2.76KB </span>","children":null,"spread":false},{"title":"kalman_filter.pyc <span style='color:#111;'> 7.39KB </span>","children":null,"spread":false}],"spread":false},{"title":"__pycache__","children":[{"title":"yolo.cpython-35.pyc <span style='color:#111;'> 4.78KB </span>","children":null,"spread":false},{"title":"yolo.cpython-37.pyc <span style='color:#111;'> 4.32KB </span>","children":null,"spread":false}],"spread":true},{"title":"yolov3.cfg <span style='color:#111;'> 8.15KB </span>","children":null,"spread":false},{"title":"tools","children":[{"title":"freeze_model.py <span style='color:#111;'> 8.28KB </span>","children":null,"spread":false},{"title":"generate_detections.py <span style='color:#111;'> 7.59KB </span>","children":null,"spread":false},{"title":"generate_detections.pyc <span style='color:#111;'> 9.07KB </span>","children":null,"spread":false},{"title":"__init__.pyc <span style='color:#111;'> 142B </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"__init__.cpython-35.pyc <span style='color:#111;'> 145B </span>","children":null,"spread":false},{"title":"generate_detections.cpython-35.pyc <span style='color:#111;'> 8.05KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"model_data","children":[{"title":"voc_classes.txt <span style='color:#111;'> 135B </span>","children":null,"spread":false},{"title":"yolo_anchors.txt <span style='color:#111;'> 76B </span>","children":null,"spread":false},{"title":"mars-small128.pb <span style='color:#111;'> 10.72MB </span>","children":null,"spread":false},{"title":"coco_classes.txt <span style='color:#111;'> 625B </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明