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 present disclosure relate to the sphere of computer expertise, and specifically, to a goal tracking method and device, a goal selection method, ItagPro a computer-readable storage medium, and digital gear. 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 extensively used in robotic navigation, itagpro locator intelligent video surveillance, iTagPro locator industrial inspection, aerospace and many different fields. It is a vital department of picture processing and computer vision disciplines, and is also the core a part of clever surveillance programs. At the same time, goal detection can also be a primary algorithm in the field of pan-identification, which performs a vital function in subsequent tasks corresponding to face recognition, gait recognition, crowd counting, and instance segmentation.

The deep learning object detection algorithm based mostly on the neural network as the principle mannequin 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 must be noted that the knowledge disclosed in the above background technology part is just used to boost the understanding of the background of the embodiments of the current disclosure, and therefore might embody info that doesn't constitute prior art known to these of ordinary skill within the artwork. 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 aim of the embodiments of the current disclosure is to supply a goal tracking method and gadget, a goal selection technique, a computer-readable storage medium, and an digital machine, a minimum of to a certain extent, to overcome the inability to concurrently optimize the detection accuracy and iTagPro locator time-consuming detection in goal 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 ItagPro advantages of the embodiments of the current disclosure shall be obvious from the following detailed description, or iTagPro locator partly realized by training the embodiments of the present 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 line with the first side of the embodiments of the current disclosure, there's provided a target monitoring method, the above-mentioned method contains: acquiring a video frame, iTagPro official performing target detection processing on the above-talked about video frame by a first detection module, and obtaining N detected targets in the above-talked about video frame , and iTagPro locator the primary coordinate data of every of the above-talked about detection targets, iTagPro smart device whereby, N is a positive integer; in line with the above-talked about first coordinate information, the partial image in the above-mentioned video frame is obtained, iTagPro locator and the i-th image corresponding to the i-th detection target is obtained; via the second detection The module performs goal detection processing on the above-talked about i-th picture to acquire the second coordinate information of the above-mentioned i-th detection goal, whereby the above-mentioned i-th detection goal is any one of many above-mentioned N detection targets, and iTagPro smart device the value of i is not larger than N A constructive integer; the monitoring of the i-th detection goal is realized through the second coordinate info of the i-th detection target.