Abstract
Infrared small target detection is still a challenge in the field of object detection. At present, although there are many related research achievements, it surely needs further improvement. This paper introduced a new application of severely occluded vehicle detection in the complex wild background of weak infrared camera aerial images, in which more than 50% area of the vehicles are occluded. We used YOLOv4 as the detection model. By applying secondary transfer learning from visible dataset to infrared dataset, the model could gain a good average precision (AP). Firstly, we trained the model in the UCAS_AOD visible dataset, then, we transferred it to the VIVID visible dataset, finally we transferred the model to the VIVID infrared dataset for a second training. Meanwhile, added the hard negative example mining block to the YOLOv4 model, which could depress the disturbance of complex background thus further decrease the false detecting rate. Through experiments the average precision improved from90.34% to 91.92%, the F1 score improved from 87.5% to 87.98%, which demonstrated that the proposed algorithm generated satisfactory and competitive vehicle detection results.
Highlights
Object detection technology has been very mature, and it has been widely used in many aspects, among which it has reached the peak in the detection of traditional images
There are some inherent defects in infrared camera images, for instance, infrared imaging is subject to imaging distance, angle of view and the change of the light, it is disturbed by the atmospheric radiation and occlusion of objects in transit of light, the imaging effect is not stable enough [11]
In view of the high false detection rate caused by the complex background, we proposed to add hard negative example mining block to the YOLOv4 model
Summary
Object detection technology has been very mature, and it has been widely used in many aspects, among which it has reached the peak in the detection of traditional images. When considering some specific application scenarios, such as the dim, weak and severely occluded vehicle detection in the infrared images under a complex background, the object detection technology still needs to be improved. The current researches focus much more on the detection of small infrared objects but ignore the impacts of the complex backgrounds, which is a challenge for detector, this paper studies on detection of the infrared objects occluded and impacted by the complex backgrounds. The associate editor coordinating the review of this manuscript and approving it for publication was Bo Pu. contrast and indistinct boundary between target and background make the detection of infrared images much harder than that of the normal datasets such as ImageNet and MS COCO. Small scale object detection is a hot and challenging task in the field of object detection. The main methods are feature fusing [14] and multi scale fusing [15]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
