Deep learning is currently the mainstream method of object detection. Faster region-based convolutional neural network (Faster R-CNN) has a pivotal position in deep learning. It impressive detection effects ordinary scenes. However, under special conditions, there can still be unsatisfactory performance, such as having problems like occlusion, deformation, or small size. This paper proposes novel and improved algorithm based on R-CNN framework combined with skip pooling fusion contextual...

Traffic sign detection and recognition plays an important role in expert systems, such as traffic assistance driving systems automatic systems. It instantly assists drivers or detecting recognizing signs effectively. In this paper, a novel approach for real-time real situation was proposed. First, the images of road scene were converted to grayscale images, then we filtered with simplified Gabor wavelets (SGW), where parameters optimized. The edges strengthened, which helpful next stage...

It well known that vehicle detection is an important component of the field object detection. However, environment particularly sophisticated in practical processes. comparatively difficult to detect vehicles various scales traffic scene images, because partially obscured by green belts, roadblocks or other vehicles, as influence some low illumination weather. In this paper, we present a model based on Faster R–CNN with NAS optimization and feature enrichment realize effective multi-scale...

Traffic sign detection systems provide important road control information for unmanned driving or auxiliary driving. In this paper, the Faster region with a convolutional neural network (R-CNN) traffic in real situations has been systematically improved. First, first step proposal algorithm based on simplified Gabor wavelets (SGWs) and maximally stable extremal regions (MSERs) is proposed. way, priori obtained will be used improving R-CNN. This part of our method named as highly possible...

Bridge crack detection is essential to ensure bridge safety. The introduction of deep learning technology has made it possible detect cracks automatically and accurately. In this study, the Inception-Resnet-v2 algorithm was systematically improved applied real-time cracks. We propose an end-to-end model based on a convolutional neural network. This combines advantages Inception convolution residual networks, broadening network width alleviating training problem calculation speed while still...

This paper addresses the challenge of small object detection in remote sensing image recognition by proposing an improved YOLOv8-based lightweight attention cross-scale feature fusion model named LACF-YOLO. Prior to backbone network outputting maps, this introduces a module, Triplet Attention, and replaces Concatenation with Fusion (C2f) more convenient higher-performing dilated inverted convolution layer acquire richer contextual information during extraction phase. Additionally, it employs...

ABSTRACT This study addresses the challenges of detecting small targets and with significant scale variations in UAV aerial images. We propose an improved YOLOv5 model, named LCM‐YOLO, to tackle these challenges. Initially, a local fusion mechanism is introduced into C3 module, forming C3‐LFM module enhance feature information acquisition during extraction. Subsequently, CCFM employed as neck structure network, leveraging its lightweight convolution cross‐scale characteristics effectively...

Existing video captioning methods usually ignore the important fine-grained semantic attributes, diversity, as well association and motion state between objects within frames. Thus, they cannot adapt to small sample data sets. To solve above problems, this paper proposes a novel model an adversarial reinforcement learning strategy. Firstly, object-scene relational graph is designed based on object detector scene segmenter express features. The encoded by neural network enrich expression of...

Large-scale explosive ordnance disposal (EOD) robotic manipulators can replace manual EOD tasks, offering higher efficiency and better safety. This study focuses on the control strategies response speeds of manipulators. Using Adams to establish dynamic model an manipulator constructing a hydraulic system in AMEsim, co-simulation is integrated. proposes PID strategy optimized by particle swarm optimization (PSO) algorithm for backpropagation (BP) neural network simulates system’s step...

Owing to the development of computerized vision technology, object detection based on convolutional neural networks is being widely used in field bridge crack detection. However, these have limited utility because low precision and poor real-time performance. In this study, an improved single-shot multi-box detector (SSD) called ISSD proposed, which seamlessly combines depth separable deformation convolution module (DSDCM), inception (IM), feature recalibration (FRM) a tightly coupled manner...

Effective intelligent fault diagnosis of bearings is important for improving safety and reliability machine. Benefiting from the training advantages, deep learning method can automatically adaptively learn more abstract high-level features without much priori knowledge. To realize representative mining automatic recognition bearing health condition, a diagnostic model stacked sparse denoising autoencoder (SSDAE) which combines (SAE) (DAE) proposed in this paper. The criterion SAE, corrupting...

Deep-learning convolutional neural networks (CNNs) have proven to be successful in various cognitive applications with a multilayer structure. The high computational energy and time requirements hinder the practical application of CNNs; hence, realization highly energy-efficient fast-learning network has aroused interest. In this work, we address computing-resource-saving problem by developing deep model, termed Gabor (Gabor CNN), which incorporates expression-efficient kernels into CNNs....

Few-shot object detection (FSOD) eliminates the dependence on tremendous instances with manual annotations in conventional detection. We deem that scarcity of positive samples is main reason restricts performance FSOD detectors. In this paper, a novel model via sample processing, namely, FSSP, proposed to detect objects accurately only few annotated samples, which based structural design Siamese network and uses YOLOv3-SPP as baseline. Central FSSP are our designed self-attention (SAM)...

Military vehicle object detection technology in complex environments is the basis for implementation of reconnaissance and tracking tasks weapons equipment, great significance information intelligent combat. In response to poor performance traditional algorithms military detection, we propose a method based on hierarchical feature representation reinforcement learning refinement localization, referred as MVODM. First, task, construct reliable dataset MVD. Second, design two strategies,...

Multispectral pedestrian detection based on deep learning can provide a robust and accurate under different illumination conditions, which has important research significance in safety. In order to reduce the log-average miss rate of object new one-stage detector suitable for multispectral is proposed. First, realize complementarity between information flows two modalities feature extraction stage loss, low-cost cross-modality complementary module (CFCM) Second, suppress background noise...

To solve the problem of low detection accuracy small objects in UAV optical remote sensing images due to contrast, dense distribution, and weak features, this paper proposes a object method based on feature alignment candidate regions is proposed for images. Firstly, AFA-FPN (Attention-based Feature Alignment FPN) defines corresponding relationship between mappings, solves misregistration features adjacent levels, improves recognition ability by aligning fusing shallow spatial deep semantic...

Bridge crack is one of the critical optical and visual information to judge health state bridges. The bridge detection methods based on artificial intelligence are essential in this field, but current approaches not satisfactory terms speed accuracy. This study proposes a novel multi-scale network, called MSCNet, comprising texture enhancement mechanism feature aggregation enhance saliency objects background for detection. We use Res2Net as backbone network improve depth expression ability...

The hydraulic pump plays a very important role in the safe and stable operation of system.Once it fails, will cause immeasurable losses to entire system.But practice, because often works under strong noise background, fault characteristics its vibration signals are weak difficult extract.To solve this problem, paper proposes an effective time series dynamic feature extraction method, which is based on complete ensemble empirical mode decomposition with adaptive (CEEMDAN) composite...

UAV remote sensing (RS) image object detection is a very valuable and challenging technology. This article discusses the importance of key features proposes an network (URSNet) based on bidirectional multi-span feature pyramid capture mechanism. Firstly, (BMSFPN) constructed. In process sampling, bicubic interpolation cross layer fusion are used to filter out noise enhance details features. Secondly, designed polarization module (FPM) uses internal attention mechanism build powerful...

Multi-object tracking (MOT) plays a crucial role in various platforms. Occlusion and insertion among targets, complex backgrounds higher real-time requirements increase the difficulty of MOT problems. Most state-of-the-art approaches adopt tracking-by-detection strategy, which relies on compute-intensive sliding windows or anchoring schemes to detect matching targets candidates each frame. In this work, we introduce more efficient effective spatial–temporal attention scheme track multiple...

The remote sensing images in large scenes have a complex background, and the types, sizes, postures of targets are different, making object detection difficult. To solve this problem, an end-to-end multi-size method based on dual attention mechanism is proposed paper. First, MobileNets backbone network used to extract multi-layer features as input MFCA, feature concentration module. MFCA employs suppress noise, enhance effective reuse, improve adaptability target through convolution...