目标检测方法、装置、电子设备及存储介质
By acquiring the initial position information and confidence level of the moving target through a target tracking algorithm and combining it with Kalman filter updates, the problem of low detection accuracy in existing technologies is solved, and higher detection accuracy is achieved.
CN115294172BActive Publication Date: 2026-07-17BEIJING BAIDU NETCOM SCI & TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING BAIDU NETCOM SCI & TECH CO LTD
- Filing Date
- 2022-07-27
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing target tracking algorithms ignore the confidence information of the detection box when detecting moving targets, resulting in low detection accuracy.
Method used
The initial position information and confidence level of the moving target are obtained by the target tracking algorithm. The target position information is determined by the confidence level and the initial position information. Kalman filtering is performed to update the target when the confidence level is low, thereby improving the detection accuracy.
Benefits of technology
This enables the acquisition of more accurate real-time location information of moving targets, thereby improving the accuracy of detection.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN115294172B_ABST
Abstract
本公开提供了一种目标检测方法、装置、电子设备及存储介质，涉及人工智能技术领域，进一步涉及图像识别、云计算和深度学习领域，以至少解决相关技术中对运动目标进行检测的检测准确率低的技术问题。具体实现方案为：获取图像序列中的目标图像，其中，目标图像为图像序列中待检测的当前图像；利用目标追踪算法对目标图像进行检测，得到运动目标的初始位置信息和初始位置信息的目标置信度，其中，目标追踪算法用于检测图像序列中每张图像的运动目标，目标置信度用于表示初始位置信息是否准确；基于目标置信度和初始位置信息，确定目标位置信息。
Need to check novelty before this filing date? Find Prior Art