Edge Assisted Object Detection for Mobile Application

Object detection and tracking is one of the key applications of wireless sensor networks (WSNs). The key issues associated with this application include network lifetime, object detection and localization accuracy. To ensure the high quality of the service, there should be a trade-off between energy efficiency and detection accuracy, which is challenging in a resource-constrained WSN. Most researchers have enhanced the application lifetime while achieving target detection accuracy at the cost of high node density. They neither considered the system cost nor the object localization accuracy. Some researchers focused on object detection accuracy while achieving energy efficiency by limiting the detection to a predefined target trajectory. In particular, some researchers only focused on node clustering and node scheduling for energy efficiency. In this study, we proposed a mobile object detection and tracking framework named the Energy Efficient Object Detection and Tracking Framework (EEODTF) for heterogeneous WSNs, which minimizes energy consumption during tracking while not affecting the object detection and localization accuracy. It focuses on achieving energy efficiency via node optimization, mobile node trajectory optimization, node clustering, data reporting optimization and detection optimization. We compared the performance of the EEODTF with the Energy Efficient Tracking and Localization of Object (EETLO) model and the Particle-Swarm-Optimization-based Energy Efficient Target Tracking Model (PSOEETTM). It was found that the EEODTF is more energy efficient than the EETLO and PSOEETTM models.

To further improve the speed and accuracy of object detection, especially small targets and occluded objects, a novel and efficient detector named YOLO-ACN is presented. The detector model is inspired by the high detection accuracy and speed of YOLOv3, and it is improved by the addition of an attention mechanism, a CIoU (complete intersection over union) loss function, Soft-NMS (non-maximum suppression), and depthwise separable convolution. First, the attention mechanism is introduced in the channel and spatial dimensions in each residual block to focus on small targets. Second, CIoU loss is adopted to achieve accurate bounding box (BBox) regression. Besides, to filter out a more accurate BBox and avoid deleting occluded objects in dense images, the CIoU is applied in the Soft-NMS, and the Gaussian model in the Soft-NMS is employed to suppress the surrounding BBox. Third, to significantly reduce the parameters and improve the detection speed, standard convolution is replaced by depthwise separable convolution, and hard-swish activation function is utilized in deeper layers. On the MS COCO dataset and infrared pedestrian dataset KAIST, the quantitative experimental results show that compared with other state-of-the-art models, the proposed YOLO-ACN has high accuracy and speed in detecting small targets and occluded objects. YOLO-ACN reaches a mAP50 (mean average precision) of 53.8% and an APs (average precision for small objects) of 18.2% at a real-time speed of 22 ms on the MS COCO dataset, and the mAP for a single class on the KAIST dataset even reaches over 80% on an NVIDIA Tesla K40.

SummaryAs various algorithms and models spring up, object detection‐based deep learning for image analysis has become an established technology in the field of computer vision. Furthermore, object detection for high‐resolution videos derived from ubiquitous surveillance cameras draws many researchers' attention due to its practical significance and the challenge on detecting accuracy and speed. Existing object detection methods mainly resize and compress each frame in the video and then apply the detection algorithm, but with the method, the detection for small objects in dense scenes is far from satisfactory in terms of accuracy because small objects are reduced to pixel‐level sizes in compressed frame images. In order to fix this issue, we propose AROD, a parallel detection framework based on adaptive image cropping. Unlike the traditional first‐compression‐and‐then‐detection methods, AROD adopts adaptive image cropping for distributed parallel detection. In this way, AROD significantly improves the accuracy of small object detection in dense scenes with acceptable overhead. In our experimental evaluation, YOLOv2‐tiny model equipped with AROD reaches 29.29 FPS along with high detection accuracy. Experimental results verify that AROD ensures the high throughput of real‐time video analytics while maintaining high detection accuracy.

Recently, drones have been applied and used in various tasks in many fields. Due to the development of camera technology and hardware, it is possible to detect objects using deep learning technology in real time. Most of the object sizes of videos and images taken by drones are very small objects. The dataset that collects these image data is the VisDrone dataset. As deep learning technology develops a lot, object detection accuracy is getting higher and higher. However, it is still hard to perform object detection in real-time and show high object detection accuracy. In this paper, we combine YOLOv5 and CBAM to increase object detection accuracy by focusing more on the features required for object detection. The model is trained using the VisDrone dataset, and the <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{mAP}$</tex> value is measured at 22. <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$56\text{mAP}$</tex> ,which is 2. <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$45\text{mAP}$</tex> higher than the original YOLOv5.

Forest fires have continually endangered personal safety and social property. To reduce the occurrences of forest fires, it is essential to detect forest fire smoke accurately and quickly. Traditional forest fire smoke detection based on convolutional neural networks (CNNs) needs many hand-designed components and shows poor ability to detect small and inconspicuous smoke in complex forest scenes. Therefore, we propose an improved early forest fire smoke detection model based on deformable transformer for end-to-end object detection (deformable DETR). We use deformable DETR as a baseline containing the best sparse spatial sampling for smoke with deformable convolution and relation modeling capability of the transformer. We integrate a Multi-scale Context Contrasted Local Feature module (MCCL) and a Dense Pyramid Pooling module (DPPM) into the feature extraction module for perceiving features of small or inconspicuous smoke. To improve detection accuracy and reduce false and missed detections, we propose an iterative bounding box combination method to generate precise bounding boxes which can cover the entire smoke object. In addition, we evaluate the proposed approach using a quantitative and qualitative self-made forest fire smoke dataset, which includes forest fire smoke images of different scales. Extensive experiments show that our improved model’s forest fire smoke detection accuracy is significantly higher than that of the mainstream models. Compared with deformable DETR, our model shows better performance with improvement of mAP (mean average precision) by 4.2%, APS (AP for small objects) by 5.1%, and other metrics by 2% to 3%. Our model is adequate for early forest fire smoke detection with high detection accuracy of different-scale smoke objects.

Object detection in videos is widely used in entertainment, robotics, surveillance etc. A major challenge in effective object detection is observed when there is occlusion, bad illumination or cluttered background. Besides, cameras do not provide any mechanism for detecting moving objects after capture. Researchers have proposed different methods for object detection in video frames, ranging from traditional to deep learning approaches. However, using the right method in the right situation for efficient and accurate detection is a concern. Even though deep learning has shown high accuracy in detection, the training and testing time and cost is a concern. In our research, we explore the best motion models for tracking objects in a video sequence. The characteristics of each model was analyzed and the results were compared using different types of videos. Our observations determine that depending on the quality of input video, traditional approaches show high accuracy in detection, comparable to state-of-the art methods.

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 surveillance system requires to achieve high accuracy of object detection at all times and to meet real-time processing requirements (30 frames per second) with high energy-efficiency. Since thermal cameras allow to see even in darkness unlike a RGB camera, object detection with a thermal camera obtains higher accuracy in the night, and thereby it has attracted much attention. However, since it is challenging to extract informative features from a thermal image, implementation challenges of an object detection with high accuracy remain. To meet the requirements, we present a sparse YOLOv2-based pedestrian detector with a thermal camera on an FPGA. For high accuracy, we propose a preprocessing that concatenates a thermal image with the background subtracted one for a detector to extract more informative features. Also, we develop a zero weight skipping architecture dedicated to our detector that contains a vectorizing unit that packs successive valid values into the same memory address to realize high parallel degree calculation. It leads to meet the real-time processing requirement with high energy-efficiency. Compared with a conventional one, F-score was 29 points higher, and speed was 3.3 times faster. Therefore, our system is more suitable for surveillance systems.

In recent years, document image understanding (DIU) has received much attention from the research community. Localizing page objects (tables, figures, equations) in document images is an important problem in DIU, which is the foundation for extracting information from document images. However, it has remained many challenges due to the high degree of intra-class variability in page document. Especially, object detection in Vietnamese image documents has still limited. In this paper, we propose CDeRSNet: a novel end-to-end trainable deep learning network to solve object detection in Vietnamese documents. The proposed network consists of Cascade R-CNN with the deformable convolution backbone and Rank & Sort (RS) Loss. CDeRSNet detects objects varying in scale with high detection accuracy at a higher IoU threshold to localize objects that differ in scale with detection accuracy at high quality. We empirically evaluate CDeRSNet on the Vietnamese image document dataset - UIT-DODV with four classes of objects: table, figure, caption, and formula. We achieved the best performance on the UIT-DODV dataset with 79.9% in terms of mAP, which is higher 5.4% than current results. In addition, we also provide a comprehensive evaluation and insightful analysis of CDeRSNet. Finally, we demonstrate CDeRSNet outperformance over state-of-the-arts models in object detection such as GFocal, GFocalV2, VFNet, DetectoRS on the UIT-DODV dataset. Code can be available at: https://github.com/trongthuan205/CDeRSNet.git .

With the rapid growth in demand for security surveillance, assisted driving, and remote sensing, object detection networks with robust environmental perception and high detection accuracy have become a research focus. However, single-modality image detection technologies face limitations in environmental adaptability, often affected by factors such as lighting conditions, fog, rain, and obstacles like vegetation, leading to information loss and reduced detection accuracy. We propose an object detection network that integrates features from visible light and infrared images—IV-YOLO—to address these challenges. This network is based on YOLOv8 (You Only Look Once v8) and employs a dual-branch fusion structure that leverages the complementary features of infrared and visible light images for target detection. We designed a Bidirectional Pyramid Feature Fusion structure (Bi-Fusion) to effectively integrate multimodal features, reducing errors from feature redundancy and extracting fine-grained features for small object detection. Additionally, we developed a Shuffle-SPP structure that combines channel and spatial attention to enhance the focus on deep features and extract richer information through upsampling. Regarding model optimization, we designed a loss function tailored for multi-scale object detection, accelerating the convergence speed of the network during training. Compared with the current state-of-the-art Dual-YOLO model, IV-YOLO achieves mAP improvements of 2.8%, 1.1%, and 2.2% on the Drone Vehicle, FLIR, and KAIST datasets, respectively. On the Drone Vehicle and FLIR datasets, IV-YOLO has a parameter count of 4.31 M and achieves a frame rate of 203.2 fps, significantly outperforming YOLOv8n (5.92 M parameters, 188.6 fps on the Drone Vehicle dataset) and YOLO-FIR (7.1 M parameters, 83.3 fps on the FLIR dataset), which had previously achieved the best performance on these datasets. This demonstrates that IV-YOLO achieves higher real-time detection performance while maintaining lower parameter complexity, making it highly promising for applications in autonomous driving, public safety, and beyond.

To realize road traffic flow surveillance under various environments which contain poor visibility conditions, we have already proposed two vehicle detection methods using thermal images taken with an infrared thermal camera. The first method uses pattern recognition for the windshields and their surroundings to detect vehicles. However, the first method decreases the vehicle detection accuracy in winter season. To maintain high vehicle detection accuracy in all seasons, we developed the second method. The second method uses tires' thermal energy reflection areas on a road as the detection targets. The second method did not achieve high detection accuracy for vehicles on left-hand and right-hand lanes except for two center-lanes. Therefore, we have developed a new method based on the second method to increase the vehicle detection accuracy. This paper proposes the new method and shows that the detection accuracy for vehicles on all lanes is 92.1%. Therefore, by combining the first method and the new method, high vehicle detection accuracies are maintained under various environments, and road traffic flow surveillance can be realized.

Abstract: Satellite image analysis plays a crucial role in fields such as environmental monitoring, urban planning, agriculture, and disaster management. This project presents a machine learning-based methodology for the automated segmentation and classification of objects in satellite images. The proposed system employs a two-step algorithm: (1) K-Means clustering for unsupervised segmentation of satellite images into meaningful clusters, and (2) Support Vector Machine (SVM) for supervised classification of the segmented regions into predefined categories such as land, water, and vegetation. A Flask-based web application is developed to provide a userfriendly interface for uploading satellite images and visualizing classified results. The backend is supported by a structured SQL database to manage image metadata and classification outputs efficiently. The system is designed to handle large datasets, ensuring robustness and scalability. Experimental results on benchmark datasets demonstrate high accuracy in object detection and classification, highlighting the system's potential to support real-world decision-making in environmental and infrastructural domains.

Improved YOLOv7 model for underwater sonar image object detection

Nowadays, increasing efficiency in the service sector by objectively monitoring and tracking business workflows has become a critical requirement for the sustainability of businesses. Traditional monitoring methods are insufficient for providing sustainable performance analysis due to their time-consuming nature and reliance on subjective human judgment. The aim of this study is to develop a system that automatically detects and classifies employee behavior using computer vision and deep learning techniques. As part of the study, data was collected using a camera placed in a real bakery environment. Five basic classes were labeled on the created data set: cleaning, product interaction, computer use, phone use, and money interaction. The current YOLOv11 (You Only Look Once) architecture, which offers high speed and accuracy for object detection and classification, was used. According to the experimental results obtained from training the model, the system demonstrated high performance, achieving 0.9552 Precision, 0.9324 Recall, 0.9437 F1-Score, and 0.9644 mAP@50 values. These results demonstrate that the proposed system can detect employee behaviors in real-time with a high accuracy rate, allowing it to be used as an effective tool in workplace productivity enhancement and performance evaluation processes.

AdaBoost algorithm based on Haar-like features can achieves high accuracy (above 95%) in object detection. Meanwhile massive computing power is needed to implement the cascaded classifiers involved in AdaBoost detection. To solve this problem, several dedicated hardware solutions have been proposed for real-time applications. In this work, a novel heterogeneous architecture of an AdaBoost detector is presented. This architecture achieves higher performance while consuming fewer hardware resources. By combining an integrated ARM Cortex-A9 processor with a dedicated accelerator, this architecture can be configured to realize various objects detection by simply loading different parameters. 2-D parallelism is involved in accelerator unit combination which brings more flexibility. This scheme is implemented on Xilinx ZC702 platform, the experiment result shows that 40 QVGA frames per second can be achieved for real-time face detection. The accelerator achieves more than 13 times improvement over the OpenCV implementation on a standalone Cortex-A9 w.r.t execution speed. Meanwhile, the accelerator consumes 40% less FPGA hardware resources than the prior-art implementation.