Contemporary image fusion methods face challenges in meeting the demands of dim nighttime environments, often accompanied by the concealment of image details in dark regions. In this article, we introduce a novel approach, named LENFusion, which achieves a beneficial interaction between low-light enhancement and image fusion in the form of a feedback loop. LENFusion is primarily divided into three components: luminance adjustment network (LAN), re-enhancement and fusion network (RFN), and luminance feedback network (LFN). The enhancement is performed in two stages. In the initial stage, LAN applies adaptive luminance adjustment to the original visible image. Subsequently, RFN achieves secondary enhancement and feature fusion with a clever combination of dual-attention mechanism, which motivates the fusion results to have high contrast and sharpness. Finally, LFN uses the luminance feedback loss to guide the luminance information of the fused images back to the LAN, effectively avoiding inappropriate enhancement of the images that do not meet the fusion requirements. In addition, we propose a reference-free color loss method for nighttime image fusion. Extensive comparison and generalization experiments have verified the superior fusion performance of LANFusion. Our code is publicly available at: https://github.com/Liling-yang/LENFsuion .

Title: Improving Street Object Detection Using Transfer Learning: From Generic Model to Specific Model | Keywords: transfer learning, SSD, object detection, fine-tune, adjusting structure | Author: Wei Liu, Shu Chen, and Longsheng Wei

We present a super perception system of intelligent vehicles for perceiving occluded street objects by collecting images from neighbor front vehicles V2V (vehicle to vehicle) video streams based on 3D projection model. This super power can avoid some serious accidents of driver-assistant systems or automatic driving systems which can only detect visible objects. Our street perception system can “see through” the front vehicles to realize detecting of the occluded street objects only by analyzing the pair images received from front and host (back) vehicles. Upon the 3D projection model based on the pair images, the system uses affine transformation to achieve augmented reality method to increase the visibility perspective of driver system. Experimental results on different datasets are shown to validate our approach. Evaluation method was first introduced into our perception system.

In a connected vehicle environment based on vehicle-to-vehicle (V2V) technology, images from front and ego vehicles are fused to augment a driver’s or autonomous system’s visual field, which is helpful in avoiding road accidents by eliminating the blind point (the objects occluded by vehicles), especially tailgating in urban areas. Realizing multi-view image fusion is a tough problem without knowing the relative location of two sensors and the fusing object is occluded in some views. Therefore, we propose an image geometric projection model and a new fusion method between neighbor vehicles in a cooperative way. Based on a 3D inter-vehicle projection model, selected feature matching points are adopted to estimate the geometric transformation parameters. By adding deep information, our method also designs a new deep-affine transformation to realize fusing of inter-vehicle images. Experimental results on KIITI (Karlsruhe Institute of Technology and Toyota Technological Institute) datasets are shown to validate our algorithm. Compared with previous work, our method improves the IoU index by 2~3 times. This algorithm can effectively enhance the visual perception ability of intelligent vehicles, and it will help to promote the further development and improvement of computer vision technology in the field of cooperative perception.