Recently, object detection has become a research hotspot in computer vision, which often detects regular images with small viewing angles. In order to obtain a field of view without blind spots, fisheye cameras, which have distortions and discontinuities, have come into use. The fisheye camera, which has a wide viewing angle, and an unmanned aerial vehicle equipped with a fisheye camera are used to obtain a field of view without blind spots. However, distorted and discontinuous objects appear in the captured fisheye images due to the unique viewing angle of fisheye cameras. It poses a significant challenge to some existing object detectors. To solve this problem, this paper proposes a PGDS-YOLOv8s model to solve the issue of detecting distorted and discontinuous objects in fisheye images. First, two novel downsampling modules are proposed. Among them, the Max Pooling and Ghost’s Downsampling (MPGD) module effectively extracts the essential feature information of distorted and discontinuous objects. The Average Pooling and Ghost’s Downsampling (APGD) module acquires rich global features and reduces the feature loss of distorted and discontinuous objects. In addition, the proposed C2fs module uses Squeeze-and-Excitation (SE) blocks to model the interdependence of the channels to acquire richer gradient flow information about the features. The C2fs module provides a better understanding of the contextual information in fisheye images. Subsequently, an SE block is added after the Spatial Pyramid Pooling Fast (SPPF), thus improving the model’s ability to capture features of distorted, discontinuous objects. Moreover, the UAV-360 dataset is created for object detection in fisheye images. Finally, experiments show that the proposed PGDS-YOLOv8s model on the VOC-360 dataset improves mAP@0.5 by 19.8% and mAP@0.5:0.95 by 27.5% compared to the original YOLOv8s model. In addition, the improved model on the UAV-360 dataset achieves 89.0% for mAP@0.5 and 60.5% for mAP@0.5:0.95. Furthermore, on the MS-COCO 2017 dataset, the PGDS-YOLOv8s model improved AP by 1.4%, AP${}_{50}$ by 1.7%, and AP${}_{75}$ by 1.2% compared with the original YOLOv8s model.

In this paper, a novel plasmonic all-optical half-subtractor and full-subtractor are designed for optical computing. The structure of plasmonic subtractors consists of a metal–insulator–metal (MIM) waveguide and rectangular ring resonators covered by a graphene layer. Due to the nonlinear optical properties of graphene, the states of the plasmonic resonators can be controlled by the pump intensity of a pump beam focused on the graphene layer. The resonators can work as all-optical switches with an ultra-fast response time to constitute optical logic devices according to the directed logic mechanism. A finite-difference time-domain method is utilized to numerically investigate the transmission of the output signals which represent the results of subtraction operations. Simulation results obtained indicate that the proposed plasmonic devices have the ability to implement half-subtraction and full-subtraction with a small feature size and fast response time, and provide a new concept and method for the design and realization of optical computing devices.

The use of 360° omnidirectional images has occurred widely in areas where comprehensive visual information is required due to their large visual field coverage. However, many extant convolutional neural networks based on 360° omnidirectional images have not performed well in computer vision tasks. This occurs because 360° omnidirectional images are processed into plane images by equirectangular projection, which generates discontinuities at the edges and can result in serious distortion. At present, most methods to alleviate these problems are based on multi-projection and resampling, which can result in huge computational overhead. Therefore, a novel edge continuity distortion-aware block (ECDAB) for 360° omnidirectional images is proposed here, which prevents the discontinuity of edges and distortion by recombining and segmenting features. To further improve the performance of the network, a novel convolutional row-column attention block (CRCAB) is also proposed. CRCAB captures row-to-row and column-to-column dependencies to aggregate global information, enabling stronger representation of the extracted features. Moreover, to reduce the memory overhead of CRCAB, we propose an improved convolutional row-column attention block (ICRCAB), which can adjust the number of vectors in the row-column direction. Finally, to verify the effectiveness of the proposed networks, we conducted experiments on both traditional images and 360° omnidirectional image datasets. The experimental results demonstrated that better performance than for the baseline model was obtained by the network using ECDAB or CRCAB.