In S502 Video Frames Are Acquired
本公开实施例涉及计算机技术领域，尤其涉及一种目标跟踪方法及装置、目标选择方法、计算机可读存储介质及电子设备。 Embodiments of the current disclosure relate to the field of laptop expertise, and in particular, to a goal monitoring method and gadget, iTagPro Item Finder a target selection technique, a pc-readable storage medium, iTagPro Item Finder and electronic tools. 目标检测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，它是图像处理和计算机视觉学科的重要分支，也是智能监控系统的核心部分。
同时目标检测也是泛身份识别领域的一个基础性的算法，对后续的人脸识别、步态识别、人群计数、实例分割等任务起着至关重要的作用。 以神经网络为主要模型的深度学习目标检测算法得到了较为快速的发展。 Object detection is broadly utilized in robot navigation, clever video surveillance, industrial inspection, aerospace and many other fields. It is a crucial department of picture processing and pc imaginative and prescient disciplines, and is also the core part of intelligent surveillance programs. At the same time, goal detection can be a fundamental algorithm in the sphere of pan-identification, which performs a significant function in subsequent tasks similar to face recognition, gait recognition, crowd counting, and occasion segmentation.
The deep learning object detection algorithm based mostly on the neural community as the principle model has been developed relatively quickly. 需要说明的是，在上述背景技术部分公开的信息仅用于加强对本公开实施例的背景的理解，因此可以包括不构成对本领域普通技术人员已知的现有技术的信息。 It needs to be famous that the data disclosed in the above background expertise section is just used to enhance the understanding of the background of the embodiments of the current disclosure, and due to this fact may include data that doesn't represent prior artwork recognized to those of abnormal talent in the art. 本公开实施例的目的在于提供一种目标跟踪方法及装置、目标选择方法、计算机可读存储介质及电子设备，至少在一定程度上克服相关技术中目标检测无法同时优化检测准确度与检测耗时的缺点。
The purpose of the embodiments of the present disclosure is to provide a target monitoring methodology and gadget, a target choice technique, a computer-readable storage medium, and an digital gadget, at the very least to a sure extent, to beat the shortcoming to simultaneously optimize the detection accuracy and time-consuming detection in target detection in associated technologies Shortcomings. 本公开实施例的其他特性和优点将通过下面的详细描述变得显然，或部分地通过本公开实施例的实践而习得。 Other features and benefits of the embodiments of the current disclosure shall be apparent from the next detailed description, or partly realized by working towards the embodiments of the current disclosure. 根据本公开实施例的第一个方面，提供一种目标跟踪方法，上述方法包括：获取视频帧，通过第一检测模块对上述视频帧进行目标检测处理，得到上述视频帧中的N个检测目标，以及每个上述检测目标的第一坐标信息，其中，N为正整数；根据上述第一坐标信息获取上述视频帧中的局部图像，得到第i检测目标对应的第i图像；通过第二检测模块对上述第i图像进行目标检测处理，以获取上述第i检测目标的第二坐标信息，其中，上述第i检测目标为上述N个检测目标中的任意一个，i取值为不大于N的正整数；通过上述第i检测目标的第二坐标信息实现上述第i检测目标的跟踪。
In accordance with the first aspect of the embodiments of the current disclosure, there's provided a goal monitoring methodology, the above-talked about technique consists of: buying a video body, performing target detection processing on the above-talked about video frame by a first detection module, and obtaining N detected targets within the above-talked about video frame , and the first coordinate info of every of the above-talked about detection targets, iTagPro Item Finder wherein, N is a constructive integer; according to the above-talked about first coordinate info, the partial image in the above-talked about video body is obtained, and the i-th picture corresponding to the i-th detection goal is obtained; through the second detection The module performs goal detection processing on the above-mentioned i-th image to acquire the second coordinate information of the above-talked about i-th detection target, wherein the above-talked about i-th detection target is any one of the above-mentioned N detection targets, and the value of i is just not better than N A constructive integer; the tracking of the i-th detection goal is realized through the second coordinate information of the i-th detection goal.