Detecting Small Objects in Thermal Images Using Single-Shot Detector
This addresses small object detection in thermal images, an incremental improvement over SSD for domain-specific applications.
The paper tackled the problem of poor small object detection in SSD by proposing DDSSD with a feature fusion module, achieving 79.7% mAP on PASCAL VOC2007 and 28.3% mmAP on MS COCO at 41 FPS, with specific gains of 10.5% on MS COCO and 22.8% on FLIR for small objects.
SSD (Single Shot Multibox Detector) is one of the most successful object detectors for its high accuracy and fast speed. However, the features from shallow layer (mainly Conv4_3) of SSD lack semantic information, resulting in poor performance in small objects. In this paper, we proposed DDSSD (Dilation and Deconvolution Single Shot Multibox Detector), an enhanced SSD with a novel feature fusion module which can improve the performance over SSD for small object detection. In the feature fusion module, dilation convolution module is utilized to enlarge the receptive field of features from shallow layer and deconvolution module is adopted to increase the size of feature maps from high layer. Our network achieves 79.7% mAP on PASCAL VOC2007 test and 28.3% mmAP on MS COCO test-dev at 41 FPS with only 300x300 input using a single Nvidia 1080 GPU. Especially, for small objects, DDSSD achieves 10.5% on MS COCO and 22.8% on FLIR thermal dataset, outperforming a lot of state-of-the-art object detection algorithms in both aspects of accuracy and speed.