Multispectral images contain rich recognition information since the multispectral camera can reveal information that is not visible to the human eye or to the conventional RGB camera. Due to this characteristic of multispectral images, multispectral face recognition has attracted lots of research interest. Although some multispectral face recognition methods have been presented in the last decade, how to fully and effectively explore the intraspectrum discriminant information and the useful interspectrum correlation information in multispectral face images for recognition has not been well studied. To boost the performance of multispectral face recognition, we propose an intraspectrum discrimination and interspectrum correlation analysis deep network (IDICN) approach. Multiple spectra are divided into several spectrum-sets, with each containing a group of spectra within a small spectral range. The IDICN network contains a set of spectrum-set-specific deep convolutional neural networks attempting to extract spectrum-set-specific features, followed by a spectrum pooling layer, whose target is to select a group of spectra with favorable discriminative abilities adaptively. IDICN jointly learns the nonlinear representations of the selected spectra, such that the intraspectrum Fisher loss and the interspectrum discriminant correlation are minimized. Experiments on the well-known Hong Kong Polytechnic University, Carnegie Mellon University, and the University of Western Australia multispectral face datasets demonstrate the superior performance of the proposed approach over several state-of-the-art methods.

In the context of edge environments with constrained resources, realizing real-time and robust crosswalk and guide arrow detection poses a significant challenge for autonomous driving systems. This paper proposes a crosswalk and guide arrow detection network (CGADNet), a lightweight visual neural network derived from YOLOv8. Specifically designed for the swift and accurate detection of crosswalks and guide arrows within the field of view of the vehicle, the CGADNet can seamlessly be implemented on the Jetson Orin Nano device to achieve real-time processing. In this study, we incorporated a novel C2f_Van module based on VanillaBlock, employed depth-separable convolution to reduce the parameters efficiently, utilized partial convolution (PConv) for lightweight FasterDetect, and utilized a bounding box regression loss with a dynamic focusing mechanism—WIoU_v3—to enhance the detection performance. In complex scenarios, the proposed method in the stability of the mAP@0.5 was maintained, resulting in a 4.1% improvement in the mAP@0.5:0.95. The network parameters, floating point operations (FLOPs), and weights were reduced by 63.81%, 70.07%, and 63.11%, respectively. Ultimately, a detection speed of 50.35 FPS was achieved on the Jetson Orin Nano. This research provides practical methodologies for deploying crosswalk and guide arrow detection networks on edge computing devices.