Small object detection is a significant and challenging research area in aerospace. Small objects often face issues like background interference and inter-class similarity due to their small size and low boundary contrast in complex environments. Physiological studies indicate that the visual pathway’s neuronal mechanisms can effectively extract features such as contours, shapes, and colors, filter out background noise and thus recognize complex forms. Therefore, this paper proposes a remote sensing small object detection model inspired by neuronal mechanisms in visual pathways, called RSVDet. RSVDet simulates the information transmission of the ventral visual pathway (Retina-LGN-V1-V2-V4-IT) and meticulously models the involved visual areas. First, inspired by the “Retina-LGN-V1” pathway, we designed a feature enhancement module to capture low-level information. Second, based on the global-local receptive field mechanism of V2 neurons, we developed a feature extraction module for shape information. Additionally, inspired by the self-regulation mechanisms of V4 neurons, we created a self-feedback attention module to filter background noise. Finally, drawing from the orientation selectivity of IT neurons, we designed a hierarchical modulation detection head module to extract complex shape features. RSVDet achieves an AP50 of 50.1% on the Visdrone dataset with 1.72M parameters, achieving the best performance among lightweight models.The code for RSVDet can be found at:https://github.com/wxz0426/RSVDet/tree/main.

Aiming at the multi-task optimization conflicts (structure-detail-denoising coupling) and high computational costs caused by existing edge detectors' reliance on complex pre-trained models, this paper proposes BCNet - the first innovative framework that synergistically integrates biological visual mechanisms and information theory to achieve triple decoupling. First, inspired by butterfly-shaped receptive fields in the visual system, we design learnable butterfly-shaped convolution kernels as fundamental operators. These kernels inherently enhance structural perception and suppress noise without requiring deep architectures and pre-training, achieving structure-denoising separation. Second, to address the detail-noise coupling issue in existing methods that reconstruct edge images from multi-scale downsampled features, we propose a conditional entropy-based uncertainty modeling approach. The uncertainty of feature loss during downsampling is quantified via Gaussian distributions, while a self-supervised mechanism dynamically assigns detaillearning weights, enabling the model to learn more details from high-uncertainty regions while avoiding noise introduction. With at most about 2M parameters and real-time inference speeds up to 152 FPS, BCNet demonstrates strong competitiveness across four benchmark datasets, providing a novel, efficient, and lightweight solution for edge detection.https://github.com/StarkLuo/BCNetCode will be available.

In industrial manufacturing, defects on the inner wall surface are crucial for quality and safety assessment. However, existing detection methods are limited by low resolution and glare interference. This study presents a Multi-morphological Feature Fusion Network for Object Detection (MFFN-OD) for 360°detection of inner wall image defects. First, it cleverly integrates panoramic imaging with conventional features through a dual-branch backbone and annular features, ensuring rotation invariance and holistic feature preservation. Second, we develop an Adaptive Multi-morphological Feature Alignment Module (AMFAM) that combats centrally polarized defects by automatically adjusting feature alignment, reducing noise, and increasing accuracy, as well as a feature interaction module with a focus on strengthening multiscale feature fusion. Third, we introduce an Asymptotic Feature Pyramid Network with Auxiliary Features (AFPN-AF) to further refine fusion, close semantic gaps, and improve performance. Experimental results show that MFFN-OD achieves 96.1% mean Average Precision (mAP) and 94.3% Average Precision (AP) for demanding faults with fast detection of 17 milliseconds per frame, meeting industrial requirements for accuracy and real-time performance.

In aerial images captured by drones or satellite remote sensing images, object information is weak and difficult to distinguish from the background, with significant variations in object sizes. Physiological research indicates that the visual system can select visual stimuli through an attention mechanism, focusing resources on processing important information while suppressing less important information. Inspired by biological vision, this article designs an object detection network, named bio-inspired remote sensing tiny object detection (BRSTD). Drawing inspiration from the parallel pathways in biological vision and the antagonistic receptive field properties of X, Y, and W cells, we designed the XYW-Conv module with antagonistic receptive fields. This module enhances the contrast between tiny objects and their surrounding information, effectively extracting tiny object information from images. To further improve the backbone network’s ability to distinguish objects from the background, we designed the XYW-Attention and applied it to the designed Backbone. To better preserve tiny object information in the shallow feature layers and suppress large object and background information, we designed a feedback suppression attention module, top-down suppression attention (TDSA), at the connection between the neck and head parts, improving the model’s performance. Experiments show that with only 1.8 M parameters, BRSTD achieved 10.4 in terms of APvt and 23.6 in terms of average precision (AP) on the AI-TOD dataset. It also performed excellently on other public remote sensing object datasets such as Visdrone and DOTA. This study not only advances remote sensing image object detection technology but also provides new ideas for the combined research of biological vision and computer vision (CV). The code will be open-sourced athttps://github.com/huangyuesheng9/BRSTD.

Recent visual odometry (VO) methods incorporating geometric algorithm into deep-learning architecture have shown outstanding performance on the challenging monocular VO task. Despite encouraging results are shown, previous methods ignore the requirement of generalization capability under noisy environment and various scenes. To address this challenging issue, this work first proposes a novel optical flow network (PANet). Compared with previous methods that predict optical flow as a direct regression task , our PANet computes optical flow by predicting it into the discrete position space with optical flow probability volume, and then converting it to optical flow. Next, we improve the bundle adjustment module to fit the self-supervised training pipeline by introducing multiple sampling, ego-motion initialization, dynamic damping factor adjustment, and Jacobi matrix weighting. In addition, a novel normalized photometric loss function is advanced to improve the depth estimation accuracy. The experiments show that the proposed system not only achieves comparable performance with other state-of-the-art self-supervised learning-based methods on the KITTI dataset, but also significantly improves the generalization capability compared with geometry-based, learning-based and hybrid VO systems on the noisy KITTI and the challenging outdoor (KAIST) scenes.

PointGoal navigation in indoor environment is a fundamental task for personal robots to navigate to a specified point. Recent studies solved this PointGoal navigation task with near-perfect success rate in photo-realistically simulated environments, under the assumptions with noiseless actuation and most importantly, perfect localization with GPS and compass sensors. However, accurate GPS signalis difficult to be obtained in real indoor environment. To improve the PointGoal navigation accuracy without GPS signal, we use visual odometry (VO) and propose a novel action integration module (AIM) trained in unsupervised manner. Sepecifically, unsupervised VO computes the relative pose of the agent from the re-projection error of two adjacent frames, and then replaces the accurate GPS signal with the path integration. The pseudo position estimated by VO is used to train action integration which assists agent to update their internal perception of location and helps improve the success rate of navigation. The training and inference process only use RGB, depth, collision as well as self-action information. The experiments show that the proposed system achieves satisfactory results and outperforms the partially supervised learning algorithms on the popular Gibson dataset.

Abstract In the past few years, contour detection algorithm has made obvious progress with the help of convolutional neural networks. The aim of this paper is to present a novel network connecting low‐ and high‐resolution features to make the network achieving richer feature representation. First, VGG net is used as encoding part with outputting the features of different resolutions, and then the feature maps are combined in some specific resolution with up‐ or down‐sample method. The combining process can be stack step‐by‐step. The proposed network makes the encoding part deeper to extract richer convolutional features. The experiments have shown that the proposed method improves the contour detection performances and outperform some existed convolutional neural networks based methods on BSDS500 and NYUD‐V2 datasets.

Significant progress has been made in boundary detection with the help of convolutional neural networks. Recent boundary detection models not only focus on real object boundary detection but also “crisp” boundaries (precisely localized along the object's contour). There are two methods to evaluate crisp boundary performance. One uses more strict tolerance to measure the distance between the ground truth and the detected contour. The other focuses on evaluating the contour map without any postprocessing. In this study, we analyze both methods and conclude that both methods are two aspects of crisp contour evaluation. Accordingly, we propose a novel network named deep refinement network (DRNet) that stacks multiple refinement modules to achieve richer feature representation and a novel loss function, which combines cross-entropy and dice loss through effective adaptive fusion. Experimental results demonstrated that we achieve state-of-the-art performance for several available datasets.

Relevant physiological studies have revealed that the response of the classical receptive field (CRF) to visual stimuli could be suppressed by non‐CRF (nCRF) inhibition of the kernel in the primary visual cortex (V1). Based on this mechanism, many bio‐inspired contour detection models have been proposed, which are mainly achieved through CRF responses and nCRF surround inhibition calculation. In fact, the dynamic characteristics of neurons play an important role in contour detection in biological vision. Inspired by these visual mechanisms, the authors propose a contour detection model that emulates these dynamic characteristics. By introducing a multi‐bandwidth Gabor filter, according to the target image, they can effectively adjust the weight ratios of the filter to protect the contours and filter the background textures in the calculation of CRF responses. Additionally, they logarithmically modulate the nCRF inhibition kernel to make texture suppression more flexible and effective, thus improving the accuracy of detection algorithm as a whole. Compared with existing bio‐inspired contour detection models, the proposed model is more effective at contour detection, which will aid engineering applications that utilise pattern recognition in machine vision.

In the mammalian primary visual cortex, the response of the classical receptive field (CRF) to visual stimuli can be suppressed by inhibition of non‐CRF (nCRF) neurons. Although many biologically plausible models based on these centre–surround interaction properties have been proposed, most of these models have failed to account for two important behaviours of neurons in the primary visual cortex (V1). First, saturation properties of neuron response. Second, the properties of fixational eye movements (FEyeMs). In the present study, the authors proposed a biologically motivated counter detection approach based on these properties. The authors’ work is significant in that they utilised a simple threshold method to ensure that CRF responses were observed within a meaningful range, and multichannel filter bank was proposed to simulate the influence of FEyeMs on nCRF. Both methods effectively preserved object contours and inhibition isolated textures. Extensive experiments indicated that the authors’ model can preserve more object contours and suppress more textures than previous biologically based models.

Psychophysical and neurophysiological investigations on the human visual system show that most neurons in the primary visual cortex (V1) possess a non‐classical receptive field (nCRF) region in addition to the CRF region. The nCRF has a modulatory, normally inhibitory, effect on the responses to visual stimuli generated within the CRF. In computational terms, this mechanism suppresses the response to edges in the presence of similar edges in the surroundings. Many computational techniques have been proposed to address the surround suppression mechanism. These methods introduce an inhibition term that is required to suppress the textures and protect the contours. Several studies have found that the spatial summation properties over the receptive fields of retinal X cells are approximately linear, while they are non‐linear for Y cells. Inspired by the visual information processing in the X–Y channel and spatial summation properties of X and Y cells, the authors propose a contour detector using linear and non‐linear modulations based on nCRF suppression. Extensive experimental evaluations demonstrate that their contour detector significantly outperforms other algorithms. The methods proposed in this study are expected to facilitate the development of efficient computational models in the field of machine vision.