Accurate detection of multiple small targets in a wide field of view based on the compound-eye imaging system.

Abstract

The compound-eye imaging system emulates the key characteristics of natural compound eyes, including an expansive field of view (FOV) and exceptional sensitivity to moving targets. These inherent properties confer distinct advantages for unmanned reconnaissance applications, facilitating both large-scale monitoring and dynamic object detection tasks. In this work, we present an innovative wide-FOV small object detection method based on the compound-eye imaging system. A convolutional attention super-resolution fusion network (CASFNet) was designed to perform super-resolution upsampling on small target features in images and adaptively fuse multi-layer features, enabling accurate identification of multiple categories of small targets in compound-eye images. In addition, we established what we believe to be a novel compound-eye sub-image (CESI) dataset that utilizes the inherent FOV-overlap among ommatidia to achieve hardware-level data enhancement, providing a robust foundation for model development and validation. Moreover, we introduced a confidence-weighted fusion strategy that exploits system-specific imaging parameters to optimize confidence scores for identical targets across different sub-images. The proposed strategy generates spatially mapped detection results with unified confidence metrics on the reconstructed full-FOV image. Experimental validation demonstrates that the method achieves outstanding performance in multi-category small object detection with a measured precision of 96.2% and mAP of 94.2%, while significantly enhancing the overall reliability of object detection based on the compound-eye imaging system. This advancement paves the way for object detection in wide-area surveillance and intelligent transportation.