Abstract. In this paper, we propose a method of object detection based on thermal images acquired from unmanned aerial vehicles (UAV). Compared with visible images, thermal images have lower requirements for illumination conditions, but they have some problems, such as blurred edges and low contrast. To address these problems, we propose to use the saliency map of thermal images for image enhancement as the attention mechanism of the object detector. In the paper, the YOLOv3 network is trained as a detection benchmark and BASNet is used to generate saliency maps from the thermal images. We fuse the thermal images with their corresponding saliency maps through the pixel-level weighted fusion method. Experiment results tested on real data have shown that the proposed method could realize the task of object detection in UAV-borne thermal images. The statistical results show that the average precisions (AP) of pedestrians and vehicles are increased by 4.5% and 2.6% respectively, compared with the benchmark of the YOLOv3 model trained on only the thermal images. The proposed model provides reliable technical support for the application of thermal images with UAV platforms.
Fixed abrasive lapping and polishing (FALP) is a new machining technology and was adopted to manufacture hard brittle materials and obtain the high productivity because of fixed abrasive. The preparation process of fixed abrasive pad (FAP) was described. FALP of K9 glass, mobile panel glass and Si were investigated with fixed 5-10 µm diamond abrasives. The effect on material removal rate (MRR) and surface quality of different materials was studied. The results show that in the same FALP process conditions, Si is the highest MRR and reaches 4428 nm/min, mobile panel glass is inferior to and K9 glass is the lowest. And surface quality of mobile panel glass that surface roughness Sa is 2.10 nm and little and less damages is the best, Si is followed and K9 glass is the worst. So FALP can obtain the higher MRR and reaches several micrometers per minute and the better quality that surface roughness Sa can reach nanometer level for different materials.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.