This disclosure relates to improved vehicle re-identification techniques. The techniques described herein utilize artificial intelligence (Al) and machine learning functions to re-identify vehicles across multiple cameras. Vehicle re-identification can be performed using an image of the vehicle that is captured from any single viewpoint. Attention maps may be generated that identify regions of thevehicle that include visual patterns that overlap between the viewpoint of the captured image and one or more additional viewpoints. The attention maps are used to generate a multi-view representation of the vehicle that provides a global view of the vehicle across multiple viewpoints. The multi-view representation of the vehicle can then be compared to previously captured image data to perform vehicle re-identification.
本公开涉及一种改进的车辆重识别技术。本文描述的技术利用人工智能(AI)和机器学习函数来重新识别通过多个摄像机的车辆。可以使用从任何单个视点捕获的车辆图像执行车辆重识别。可以生成标识车辆的区域注意力图,该区域包括捕获图像的视点与一个或多个其他视点之间重叠的视觉图形。注意力图用于生成车辆的多视图表示,车辆的多视图表示提供车辆的多个视点的全局视图。然后可以将车辆的多视图表示与先前捕获的图像数据进行比较,以执行车辆重识别。
Vehicle re-identification techniques using neural networks for image analysis, viewpoint-aware pattern recognition, and generation of multi-view vehicle representations
利用神经网络进行图像分析、视点感知模式识别以及生成多视图车辆表示的车辆重识别技术
2020-10-27
Patent
Elektronische Ressource
Chinesisch
Europäisches Patentamt | 2019
|Europäisches Patentamt | 2022
|Real-time vehicle orientation classification and viewpoint-aware vehicle re-identification
BASE | 2021
|