Target detection model training and target detection method, device, equipment and medium
By fusing reliable and ambiguous images and using a region proposal network for label correction, the problem of unreliable manual labeling in X-ray security inspection scenarios is solved, thereby improving the training stability and detection accuracy of the target detection model.
CN116051955BActive Publication Date: 2026-05-26ZHEJIANG PECKERAI TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHEJIANG PECKERAI TECH CO LTD
- Filing Date
- 2022-12-22
- Publication Date
- 2026-05-26
Smart Images
Figure CN116051955B_ABST
Abstract
This invention discloses a method, apparatus, device, and medium for training an object detection model and for object detection, relating to the field of computer vision technology. The method includes: fusing a reliable image and an ambiguous image to obtain a fused image; the reliable image is an image that does not contain ambiguous object regions, and the ambiguous image is an image that contains at least one ambiguous object region; inputting the fused image into a region proposal network to obtain candidate regions in the fused image; correcting the labels of ambiguous object regions in the ambiguous image based on the candidate regions in the fused image; and training a model to be trained based on the corrected labels to obtain an object detection model. The technical solution of this invention can solve the problem of difficult manual labeling of ambiguous targets, reduce the interference of noisy targets on the model, and improve the stability of model training.
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
Training image classification model, image classification method and device, equipment and medium
CN111382758A
Target detection model training method, device and computer storage medium
CN113591885A