GigaMoE: Sparsity-Guided Mixture of Experts for Efficient Gigapixel Object Detection

With the rapid development of autonomous driving technology, traditional object detection algorithms often face challenges such as the trade-off between model parameters and recognition accuracy, insufficient detection accuracy, and slow detection speed when dealing with vehicle and pedestrian detection tasks in complex scenarios. To address these challenges, we propose a novel lightweight real-time driving scene detection network, FEEP-YOLO. Based on the YOLOv8 algorithm, our network not only maintains high detection accuracy but also achieves faster training speed and fewer model parameters. FEEP-YOLO employs a lightweight network, Faster Net, to significantly reduce model parameters, thereby accelerating detection speed and better meeting real-time requirements. To further improve detection accuracy, we introduce an EMA attention module into the network and optimize the bounding box loss function, adopting the EIOU loss function to enhance target features and reduce background interference. Additionally, to detect small objects more accurately, we add feature layers rich in semantic information to the detection end. Experimental results demonstrate that FEEP-YOLO outperforms YOLOv8 in terms of both detection speed and accuracy on the KITTI and SODA datasets, while significantly reducing the number of model parameters and model size. FEEP-YOLO achieves high detection speed while improving detection accuracy and reducing computational resource consumption, meeting the practical application requirements under limited computing power, memory space and power consumption. The key contribution of FEEP-YOLO lies in its ability to balance accuracy speed, and efficiency, making it a robust solution for real-time autonomous driving applications in complex environments.

A challenging and attractive task in computer vision is underwater object detection. Although object detection techniques have achieved good performance in general datasets, problems of low visibility and color bias in the complex underwater environment have led to generally poor image quality; besides this, problems with small targets and target aggregation have led to less extractable information, which makes it difficult to achieve satisfactory results. In past research of underwater object detection based on deep learning, most studies have mainly focused on improving detection accuracy by using large networks; the problem of marine underwater lightweight object detection has rarely gotten attention, which has resulted in a large model size and slow detection speed; as such the application of object detection technologies under marine environments needs better real-time and lightweight performance. In view of this, a lightweight underwater object detection method based on the MobileNet v2, You Only Look Once (YOLO) v4 algorithm and attentional feature fusion has been proposed to address this problem, to produce a harmonious balance between accuracy and speediness for target detection in marine environments. In our work, a combination of MobileNet v2 and depth-wise separable convolution is proposed to reduce the number of model parameters and the size of the model. The Modified Attentional Feature Fusion (AFFM) module aims to better fuse semantic and scale-inconsistent features and to improve accuracy. Experiments indicate that the proposed method obtained a mean average precision (mAP) of 81.67% and 92.65% on the PASCAL VOC dataset and the brackish dataset, respectively, and reached a processing speed of 44.22 frame per second (FPS) on the brackish dataset. Moreover, the number of model parameters and the model size were compressed to 16.76% and 19.53% of YOLO v4, respectively, which achieved a good tradeoff between time and accuracy for underwater object detection.

The continuing development of remote sensing has resulted in a rapidly increasing number of remote sensing applications. High-resolution remote sensing images are used in various fields in the military. We propose methods for object detection based on remote sensing images. We develop a signal processing method for normalizing remote sensing images to eliminate noise such as fog, haze, and poor lighting. This method further improves detection accuracy and reduces error rates. We develop YOLOv4-faster, an accelerated neural network model based on the YOLO (You-Only-Look-Once) object detection method. YOLOv4-faster outperforms existing networks in terms of execution time and detection performance. We conduct a series of experiments on two public datasets (TGRS-HRRSD and NWPU VHR-10) as well as a dataset containing six military target classes provided by IMINT & Analysis and collected from Google Earth. YOLOv4-faster improves efficiency by utilizing multi-scale operations for the accurate detection of objects of various sizes, especially small objects. The experimental results show improved mAP (mean average precision) performance of the proposed method for object detection in remote sensing images. We thus propose a novel system for automatic object detection for high-resolution remote sensing images.

We propose methods for object detection based on remote sensing images. This method further improves detection accuracy and decreases error rates. Modified YOLOv4 is an accelerated neural network model based on the YOLO (YouOnly-Look-Once) object detection method. It outperforms existing networks in terms of execution time and detection performance. The experimental results show improved mAP (mean average precision) performance of the proposed method for object detection in remote sensing images. We thus propose a novel system for automatic object detection for high-resolution remote sensing images.

Unmanned Aerial Vehicle (UAV) image object detection plays a crucial role in various fields. However, compared with natural images, UAV images are characterized by significant target scale variations, complex backgrounds, dense small targets, and clustered target distributions, which pose serious challenges to object detection tasks. To address these issues, this study proposes an improved object detection algorithm named MFRA-YOLO, which combines multi-scale feature fusion and receptive-field attention-based convolution, built upon the baseline YOLOv8n algorithm. First, Monte Carlo attention is integrated into receptive-field attention-based convolution to enhance cross-scale information interaction capability, thereby forming a novel convolutional module for downsampling operations. Second, a multi-scale selective fusion module is incorporated into the feature fusion network to enable adaptive cross-scale integration of features. When coupled with the scale sequence feature fusion module, this integration significantly enhances the detection performance for small targets. Finally, the Focaler-PIoUv2 loss function is designed to replace the CIoU in the baseline algorithm. This replacement allows the algorithm to better balance hard and easy samples and improve detection accuracy. Experimental results on the public dataset VisDrone2019 show that MFRA-YOLO achieves superior accuracy-efficiency tradeoffs compared to the baseline YOLOv8n and other YOLO variants. Compared to YOLOv8n, MFRA-YOLO improves mAP50 by 3.5% and mAP50:95 by 2.3%, respectively. These performance gains are accompanied by only modest increases in parameter count and computational cost. Notably, while maintaining performance at 143 FPS, thereby satisfying the real-time deployment requirements for UAVs. Furthermore, compared with several state-of-the-art algorithms designed for UAV scenarios, MFRA-YOLO also offers distinct advantages. To verify the generalization ability and stability of MFRA-YOLO, comparative experiments are carried out on the RSOD dataset, where our algorithm consistently demonstrates excellent detection performance. Overall, these results confirm that MFRA-YOLO not only improves the detection performance for UAV imagery substantially but also achieves an excellent balance between detection accuracy and efficiency.

Image restoration tasks such as deraining, deblurring, and dehazing are crucial for enhancing the environmental perception of autonomous vehicles and traffic systems, particularly for tasks like vehicle detection, pedestrian detection and lane line identification. While transformer-based models excel in these tasks, their prohibitive computational complexity hinders real-world deployment on resource-constrained platforms. To bridge this gap, this paper introduces a novel Soft Knowledge Distillation (SKD) framework, designed specifically for creating highly efficient yet powerful image restoration models. Our core innovation is twofold: first, we propose a Multi-dimensional Cross-Net Attention(MCA) mechanism that allows a compact student model to learn comprehensive attention relationships from a large teacher model across both spatial and channel dimensions, capturing fine-grained details essential for high-quality restoration. Second, we pioneer the use of a contrastive learning loss at the reconstruction level, treating the teacher’s outputs as positives and the degraded inputs as negatives, which significantly elevates the student’s reconstruction quality. Extensive experiments demonstrate that our method achieves a superior trade-off between performance and efficiency, notably enhancing downstream tasks like object detection. The primary contributions of this work lie in delivering a practical and compelling solution for real-time perceptual enhancement in autonomous systems, pushing the boundaries of efficient model design.

Software was developed in Python for the digital processing of object images before their detection using the You Only Look Once (YOLO) artificial neural network. Detection was carried out on object images, specifically vehicles and other road users. The preprocessing of images was performed through histogram equalization and local contrast enhancement. The original images were read from video cameras or graphic files. Image detection was performed using the medium-sized YOLO convolutional neural network model, YOLOv8m. As a result of detection, the studied objects, particularly cars, were highlighted with rectangular bounding boxes. To evaluate the accuracy of object detection, several metrics (parameters) were used: Precision, Recall, Intersection over Union (IoU), F1, and Average Precision (AP). The YOLO network was pre-trained on the Common Objects in Context dataset. The YOLO neural network returns the object recognition confidence, the coordinates of its center (x, y) on the image, and its width and height (w, h). The detected objects are marked with rectangular bounding boxes. The positioning of objects in the images was manually performed using the Roboflow tool, which allows for accurate spatial positioning of each object. The study of the impact of image preprocessing on the accuracy of object detection by the YOLO network was conducted using a typical traffic scene image. After histogram equalization, the histogram becomes more symmetrical and uniform, improving the visual quality of both dark and bright areas. This led to improved object detection accuracy across almost all metrics. The increase in detection accuracy by the IoU parameter is 0.169. The summary improvement in detection accuracy by the IoU, F1, AP parameters is 0.502. It was shown that after image preprocessing, detection accuracy increased, and all vehicles were correctly detected. The developed software can be used in various computer vision systems as well as in Internet of Things systems for remote monitoring and control.

In the mining industry, lithological identification is crucial for ensuring the safety of equipment and personnel, as well as for improving production efficiency. Traditional ore identification methods, such as visual inspection, physical testing, and chemical analysis, have many limitations in terms of their operational complexity and applicability. Modern ore identification technologies, especially those combined with deep learning methods, can effectively overcome these shortcomings and significantly enhance identification performance. However, mainstream deep learning object detection algorithms still face the issues of low accuracy and poor identification performance in challenging mining conditions. To handle these problems, an improved Faster R-CNN model is proposed in this study. Specifically, we replace the backbone network ResNet with Res2Net-50 and incorporate an improved Feature Pyramid Network (FPN) to enhance feature fusion, thereby further improving the model’s feature extraction capability. Region of Interest(ROI) Align replaces the ROI pooling layer to solve the spatial misalignment issue, providing a higher detection accuracy in tasks involving small object detection and precise boundary detection. Additionally, the backbone feature extraction network integrates an efficient channel attention (ECA) module to optimize high-resolution semantic information maps. By adding simulated noise, the model’s robustness and anti-interference capabilities are enhanced. Soft-NMS is used instead of traditional NMS, preserving more potential targets through a confidence decay mechanism, thereby improving the detection accuracy and robustness. The experimental results show that the improved Faster R-CNN model maintains efficient and accurate ore identification capabilities even in complex mining environments, demonstrating its great potential in practical applications. The model achieves significant improvements in detection accuracy and efficiency, providing strong support for the intelligent and automated identification of ores.

To solve the performance degradation of visible light-based object detectors affected by low-light environments, an attention-guided detection model based on adaptive depthwise convolution is proposed. First, the quality of the original image is improved, and various image information is restored by an image enhancement module named zero-reference dual-illumination deep-curve estimation++ (Zero-DiDCE++). Then, the article further introduces a self-attention mechanism and receptive field features, designing the feature self-attention (FSA) module and the sparse receptive field adaptive depth convolution (SRDConv) module. These modules work in concert to accentuate target features and improve detection accuracy. Finally, we introduce a framework named ZRF-you only look once (YOLO)v9 for object detection, which is designed to improve performance in low-light conditions. It incorporates Zero-DiDCE++ and connects it with an improved YOLOv9 network for algorithm integration. Experiments show that based on the ExDark, Dark Face, and Tiny-Person datasets, the ZRF-YOLOv9 algorithm improves the low-light detection accuracy by 1.1%, 2.0%, and 0.5% in mAP ${}_{5}{}_{0}$ . This model not only enhances the visibility of the image but also improves detection accuracy for target images in low-light scenes.

Iterative application of generative adversarial networks for improved buried pipe detection from images obtained by ground‐penetrating radar

Intelligent surveillance systems enable secured visibility features in the smart city era. One of the major models for pre-processing in intelligent surveillance systems is known as saliency detection, which provides facilities for multiple tasks such as object detection, object segmentation, video coding, image re-targeting, image-quality assessment, and image compression. Traditional models focus on improving detection accuracy at the cost of high complexity. However, these models are computationally expensive for real-world systems. To cope with this issue, we propose a fast-motion saliency method for surveillance systems under various background conditions. Our method is derived from streaming dynamic mode decomposition (s-DMD), which is a powerful tool in data science. First, DMD computes a set of modes in a streaming manner to derive spatial–temporal features, and a raw saliency map is generated from the sparse reconstruction process. Second, the final saliency map is refined using a difference-of-Gaussians filter in the frequency domain. The effectiveness of the proposed method is validated on a standard benchmark dataset. The experimental results show that the proposed method achieves competitive accuracy with lower complexity than state-of-the-art methods, which satisfies requirements in real-time applications.

The task of object detection is to accurately and efficiently identify and locate a large number of predefined categories of object instances from images. With the wide application of deep learning, the accuracy and efficiency of target detection have been greatly improved. However, deep learning-based target detection still faces challenges from key technologies such as improving and optimizing the performance of mainstream target detection algorithms, improving the detection accuracy of small target objects, realizing multi-class object detection and lightweight detection model. In response to the above challenges, based on extensive literature research, this paper analyses methods for lightweight detection models and improved detection accuracy from the perspective of YOLOv5s network structure. The problems to be solved in target detection and the future research direction are predicted and prospected.

Object detection is a common and challenging problem in today's world. Also due to the rapid development of deep learning employing underlying deep models over the past ten years, many researchers have investigated and contributed to improving the performance of object identification and associated tasks such as object classification, localization, and segmentation. Inference time and detection accuracy are used to rate the effectiveness of any object detector. In terms of detection accuracy, it is observed that the two-stage detectors outperform the single-stage detector however, single-stage detectors outperform their rivals in terms of inference time. Additionally, You Only Look Once (YOLO) and its versions have improved detection accuracy, some-times surpassing two-stage detectors. In this study, we performed a co-design methodology for hardware and software (HW/SW) aimed at Central Processing Unit (CPU) + Field Programmable Gate Array (FPGA) based heterogeneous platform which is Xilinx FPGA Kria KV260. A CNN-based algorithm is first extended to the YOLOv4, v5L, and v5s framework before being implemented on the Kria KV260, an out-of-the-box platform for developing advanced vision applications. A reduced computation time is observed for the deployment of the Machine Learning model on Kria KV260.

As the core component of electronic products, the quality of PCB (print circuit board) directly affects the performance and reliability of the entire product. The traditional PCB defect detection methods mainly rely on manual visual inspection and image processing technology, which have problems such as low efficiency and easy errors and cannot meet the needs of large-scale production. The PCB defect detection method based on deep learning and object detection technology has gradually become mainstream. This article focuses on the research of PCB defect object detection method based on deep learning. Therefore, the paper conducts relevant intensive study on PCB defect detection, aiming to develop a model that is accurate, compact, and suitable for real-time detection. Specific improvements include using C2F_The ViT module replaces the original C2F, and the purpose is to facilitate the model to comprehensively consider the local details of PCB defects and the global contextual semantic information. Introduces multi-head self-attention mechanism (MHSA), adds detection heads in the p2 layer, and improves defect detection accuracy and location accuracy. Extract the target semantic information of small defects and suppress the local background information at the same time. The experimental results indicate that the detection algorithm can improve detection accuracy. Compared with the original YOLOv8, the improved model has a 4.9% and 7.9% improvement in map50 and map50-95, respectively.

Image recognition technology plays an important role in advanced driver assistance systems (ADAS). The objective of this study is to explore the feasibility of using heterogeneous image fusion to improve the object detection performance of the ADAS. Among the many possible combinations of image types, the fusion of infrared (IR) and visible (VIS) images has great potential because of their complementary characteristics. Most studies on image fusion assume that the images involved align themselves perfectly, which is unrealistic. We address this alignment issue in this study, review various methods of image alignment and fusion, and propose an image-fusion approach that combines alignment and fusion methods for the ADAS application. Finally, we used deep learning networks to detect pedestrian and vehicle objects before and after the image fusion. The experimental results show that the fusion of IR and VIS images can improve the object detection performance of deep-learning networks. Compared with previous studies on fusion, the proposed approach ranks top if the detection accuracy improvement and execution speed are considered as a whole. This study also found that, to use image fusion to improve the object detection accuracy of deep learning networks, it is better to use fused images directly instead of unfused VIS images as the training samples.