中国科学院自动化研究所机构知识库

Structural information is an essential component for efficient object detection. In many visual detection tasks, the objects with large structural deformation usually make up a large proportion. The shape, con-tour, and internal structure of the objects tend toward dramatic change, which easily causes troubles for efficient object detection. Therefore, how to detect these objects robustly and accurately is one of the sig-nificant challenges. To address this issue, we introduce a Cross Stage Partial connections-based weighted Bi-directional Feature Pyramid Network (CSP-BiFPN), which allows easy and efficient multi-scale feature fusion by cross-stage partial connections. Second, to enhance the model's spatial transformation capacity, the multi-scale feature maps extracted from the YOLO backbone network are processed by an enhanced spatial transformation network (ESTN) for spatial deformations. Based on these architectural modifica-tions and optimizations, we further develop a novel real-time robust object detection model called Bi-STN-YOLO. We evaluate the performance of the proposed method on four image datasets. The experi-mental results demonstrate that the proposed approach achieves significant improvements compared with the typical YOLO families and competitive performance compared to the state-of-the-arts in detec-tion tasks. (c) 2022 Elsevier B.V. All rights reserved.