In the past ten years, multimodal image registration technology has been continuously developed, and a large number of researchers have paid attention to the problem of infrared and visible image registration. Due to the differences in grayscale distribution, resolution and viewpoint between two images, most of the existing infrared and visible image registration methods are still insufficient in accuracy. To solve such problems, we propose a new robust and accurate infrared and visible image registration method. For the purpose of generating more robust feature descriptors, we propose to generate feature descriptors using a concentric-circle-based feature-description algorithm. The method enhances the description of the main direction of feature points by introducing centroids, and, at the same time, uses concentric circles to ensure the rotation invariance of feature descriptors. To match feature points quickly and accurately, we propose a multi-level feature-matching algorithm using improved offset consistency for matching feature points. We redesigned the matching algorithm based on the offset consistency principle. The comparison experiments with several other state-of-the-art registration methods in CVC and homemade datasets show that our proposed method has significant advantages in both feature-point localization accuracy and correct matching rate.

Infrared pedestrian target detection is affected by factors such as the low resolution and contrast of infrared pedestrian images, as well as the complexity of the background and the presence of multiple targets occluding each other, resulting in indistinct target features. To address these issues, this paper proposes a method to enhance the accuracy of pedestrian target detection by employing contour information to guide multi-scale feature detection. This involves analyzing the shapes and edges of the targets in infrared images at different scales to more accurately identify and differentiate them from the background and other targets. First, we propose a preprocessing method to suppress background interference and extract color information from visible images. Second, we propose an information fusion residual block combining a U-shaped structure and residual connection to form a feature extraction network. Then, we propose an attention mechanism based on a contour information-guided approach to guide the network to extract the depth features of pedestrian targets. Finally, we use the clustering method of mIoU to generate anchor frame sizes applicable to the KAIST pedestrian dataset and propose a hybrid loss function to enhance the network’s adaptability to pedestrian targets. The extensive experimental results show that the method proposed in this paper outperforms other comparative algorithms in pedestrian detection, proving its superiority.

In recent years, deep learning models have achieved great success in the field of semantic segmentation,which achieve satisfactory performance by introducing a large number of parameters. However, this achievement usually leads to high computational complexity, which seriously limits the deployment of semantic segmented applications on mobile devices with limited computing and storage resources. To address this problem, we propose a lightweight asymmetric spatial feature network (LASNet) for real-time semantic segmentation. We consider the network parameters, inference speed, and performance to design the structure of LASNet, which can make the LASNet applied to embedded devices and mobile devices better. In the encoding part of LASNet, we propose the LAS module, which retains and utilize spatial information. This module uses a combination of asymmetric convolution, group convolution, and dual-stream structure to reduce the number of network parameters and maintain strong feature extraction ability. In the decoding part of LASNet, we propose the multivariate concatenate module to reuse the shallow features, which can improve the segmentation accuracy and maintain a high inference speed. Our network attains precise real-time segmentation results in a wide range of experiments. Without additional processing and pre-training, LASNet achieves 70.99% mIoU and 110.93 FPS inference speed in the CityScapes dataset with only 0.8 M model parameters.