Exploiting the ACCuracy-ACCeleration tradeoff: VINS-assisted real-time object detection on moving systems

Object detection algorithms using convolutional neural networks (CNNs) achieve high detection accuracy, but it is challenging to realize real-time object detection due to their high computational complexity, especially on resource-constrained mobile platforms. In this article, we propose an algorithm-hardware co-optimization approach to designing a real-time object detection system. We first develop a compact object detection model based on a binarized neural network (BNN), which employs a new layer structure, the DenseToRes layer, to mitigate information loss due to deep quantization. We also propose an efficient object detection processor that runs object detection with high throughput using limited hardware rescources. We develop a resource-efficient processing unit supporting variable precision with minimal hardware overheads. Implemented in field-programmable gate array (FPGA), the object detection processor achieves 64.51 frames/s throughput with 64.92 mean average precision (mAP) accuracy. Compared to prior FPGA-based designs for object detection, our design achieves high throughput with competitive accuracy and lower hardware implementation costs.

Real-time object detection and tracking in video streams has become a fundamental component of modern intelligent systems, enabling applications in surveillance, autonomous driving, robotics, healthcare monitoring, and smart cities. The rapid advancement of deep learning techniques has significantly improved the accuracy and efficiency of detecting and tracking multiple objects under complex and dynamic environments. This study presents a deep learning–based framework for real-time object detection and tracking in continuous video streams, emphasizing both computational efficiency and detection robustness.The proposed system integrates a state-of-the-art convolutional neural network (CNN)-based object detector with a reliable multi-object tracking algorithm. The detection module identifies objects of interest in each frame, while the tracking component maintains consistent identities across consecutive frames by utilizing motion prediction and feature association strategies. To achieve real-time performance, the model is optimized through lightweight network architectures and parallel processing on GPU hardware. Data augmentation and transfer learning techniques are employed to enhance generalization and reduce training time. Performance evaluation is conducted on benchmark video datasets using standard metrics such as precision, recall, mean Average Precision (mAP), and tracking accuracy. Experimental results demonstrate that the proposed framework achieves high detection accuracy while maintaining low latency, making it suitable for real-time deployment. Furthermore, the system effectively handles challenges such as occlusion, scale variation, and illumination changes. This research presents a comprehensive study on real-time object detection and tracking in video streams using deep learning techniques. The proposed framework integrates YOLO-based object detection with Deep SORT multi-object tracking to achieve robust spatial localization and temporal identity preservation. The study evaluates performance using benchmark datasets including COCO, MOT17, and KITTI. Mathematical formulations of detection loss, Kalman filtering, and data association are presented. Experimental analysis using precision, recall, mAP, MOTA, ROC-AUC, and PR-AUC demonstrates that the system achieves high detection accuracy while maintaining real-time performance above 35 frames per second. The findings confirm that deep learning-based frameworks provide scalable and efficient solutions for surveillance, autonomous vehicles, and intelligent monitoring systems.

The real-time detection of objects and persons in their approach remains vital for applications that need safety measures security protocols and efficiency in autonomous systems and surveillance operations and industrial automation. The proposed research creates a durable real-time detection system through sensor combination using ultrasonic along with infrared and LiDAR and radar sensors and computer vision-based sensors to enhance detection accuracy and response times in changing environmental scenarios. The method starts by processing data gathered from arrays of multiple sensors through optimized filtering techniques and extraction methods before machines learn to classify objects while reducing false detection instances. The assessment of performance takes place in different environmental conditions to track both detection speed along with accuracy levels and system reliability. Sensor fusion enables real-time detection systems to perform better because it reduces the impact of environmental changes and sensor distortions. System capabilities increase in different operational areas when researchers demonstrate pre-processing optimization works alongside intelligent data processing systems. The research findings combine autonomous navigation systems with smart surveillance technology together with safety protocols for industrial security which enable real-time scalability and reduced risk elements. Research demonstrates a specific achievement through its analysis that machines learn better when combined with multi-sensor integration over single-sensor models which improves system reliability when used in real-world applications. Multi-sensor arrays and advanced processing techniques generate enhanced system responsiveness alongside increased adaptability and reliability thus improving detection systems within industrial security measures and automation operations.

Object detection is a major branch and fundamental task in computer vision, aiming to localize, identify and classify even the smallest objects of interest in images. Features can be extracted efficiently by deep convolutional neural networks (CNNs) as the backbone for real-time or near real-time object detection performance than the hand-crafted-based traditional methods. In the past few years, the advent of transformer-based models with robust self-attention mechanisms has not only raised object detection performance to a higher level but has also enabled it to produce excellent results. Many object detection tasks in the real world require that 3D information about the object be obtained, thus strengthening active research in 3D object detection. However, the algorithms for detecting 3D objects are not easy to propagate in real-world applications due to many factors, making reconstruction of 2D object detection algorithms to 3D object detection algorithms the suitable alternative. Therefore, we review the evolution of 2D object detection algorithms for digital imaging applications, focusing on their developments, models, applications, datasets, evaluation metrics, strengths and weaknesses, for better understanding of their landmarks and contributions to the advancement of the field.

This research proposes a novel hardware-optimized design to accelerate Convolutional Neural Networks (CNNs) using Verilog HDL. The design is specifically developed for the DARKNET-19 system model, which serves as the backbone of the YOLOv3-tiny algorithm, a widely used framework for real-time object detection in dynamic environments. The CNN architecture was implemented in Verilog HDL and synthesized using Synopsys Design Compiler, with a focus on improving both object detection accuracy and hardware resource efficiency. The proposed design efficiently performs key CNN operations, including convolution, pooling, and activation, enabling faster real-time object detection compared to many existing methods. To improve performance, the hardware design incorporates parallel processing techniques, allowing multiple computations to be executed simultaneously. This significantly reduces the system latency and power consumption. The convolutional layers of the DARKNET-19 architecture are efficiently mapped onto the hardware platform, ensuring optimized data storage and fast memory access, which further enhances processing speed and detection accuracy. An innovative feature of the design is a 2-dimensional image preprocessing module that prepares input images before they are fed into the CNN. This preprocessing stage includes image resizing, brightness normalization, and color adjustment, which helps the CNN process visual data more effectively. After preprocessing, the images pass through several CNN layers. The convolutional layers extract key features from the images, while the pooling and activation layers refine these features to improve detection performance. Finally, the processed data is analyzed by the YOLOv3-tiny algorithm, which identifies and locates objects in the images with high precision. Experimental results demonstrate that the proposed high-speed and resource-efficient hardware architecture is well-suited for real-time object detection applications, particularly in highly dynamic and unpredictable environments.

For real-time object detection and speech alarms, Research offers a sophisticated blind aid solution that smoothly combines the YOLO algorithm with Open CV's DNN (Deep Neural Network) module. The main objective is to improve the safety and freedom of people with visual impairments by offering quick object recognition and audio feedback. The YOLO method, which is tuned for real-time inference, is used by the system to precisely recognize objects after using a webcam to record live video input. Then, using audio description, it produces speech notifications that provide crucial details about the things it has spotted. Because of its exceptional versatility, the research can provide speech outputs in the user's preferred language, increasing its usability and accessibility. Its versatility is further demonstrated by its capacity to precisely handle a variety of object classes, making it a priceless tool for greatly enhancing the lives of those who are blind or visually impaired. Challenges in real-time object detection include occlusion, scale variations, and cluttered environments. Researchers must navigate the trade-offs between accuracy and speed. Real- time object detection is pivotal in computer vision, enabling intelligent systems across diverse applications. Real-time object detection systems designed for assistive technologies are becoming increasingly important in empowering individuals with visual impairments. The research integrates the YOLO algorithm with OpenCV’s DNN module to deliver a highly responsive blind-aid solution capable of capturing live video through a webcam and processing it instantly. YOLO’s architecture, optimized for speed and accuracy, enables the system to detect and classify multiple objects within each video frame, even in dynamic or unpredictable environments. Once an object is identified, the system generates immediate speech output, providing descriptive audio alerts in the user’s preferred language, thus enhancing accessibility and user experience. This multilingual capability makes the solution versatile across different regions and cultures. Additionally, the system supports a wide range of object categories such as vehicles, household items, and obstacles helping visually impaired users navigate daily surroundings more safely and independently. However, the implementation faces challenges, including handling occlusions, varying object scales, low-light conditions, and cluttered backgrounds. These factors require careful balancing between detection accuracy and processing speed to maintain real-time performance. Despite these challenges, the integration of advanced deep learning models with user-friendly audio interfaces demonstrates significant potential to improve mobility, safety, and overall quality of life for people with visual impairments.

Tiny object detection is an important and challenging object detection subfield. However, many of its numerous applications (e.g., human tracking and marine rescue) have tight detection time constraints. Namely, two-stage object detectors are too slow to fulfill the real-time detection needs, whereas one-stage object detectors have an insufficient detection accuracy. Consequently, enhancing the detection accuracy of one-stage object detectors has become an essential aspect of real-time tiny objects detection. This work presents a novel model for real-time tiny objects detection based on a one-stage object detector YOLOv5. The proposed YOLO-P4 model contains a module for detecting tiny objects and a new output prediction branch. Next, a weighted bi-directional feature pyramid network (BiFPN) is introduced in YOLO-P4, yielding an improved model named YOLO-BiP4 that enhances the YOLO-P4 feature input branches. The proposed models were tested on the Tiny-Person dataset, demonstrating that the YOLO-BiP4 model outperforms the original model in detecting tiny objects. The model satisfies the real-time detection needs while obtaining the highest accuracy compared to existing one-stage object detectors.

Computer vision (CV) and human-computer interaction (HCI) are essential in many technological fields. Researchers in CV are particularly interested in real-time object detection techniques, which have a wide range of applications, including inspection systems. In this study, we design and implement real-time object detection and recognition systems using the single-shoot detector (SSD) algorithm and deep learning techniques with pre-trained models. The system can detect static and moving objects in real-time and recognize the object's class. The primary goals of this research were to investigate and develop a real-time object detection system that employs deep learning and neural systems for real-time object detection and recognition. In addition, we evaluated the free available, pre-trained models with the SSD algorithm on various types of datasets to determine which models have high accuracy and speed when detecting an object. Moreover, the system is required to be operational on reasonable equipment. We tried and evaluated several deep learning structures and techniques during the coding procedure and developed and proposed a highly accurate and efficient object detection system. This system utilizes freely available datasets such as MS Common Objects in Context (COCO), PASCAL VOC, and Kitti. We evaluated our system's accuracy using various metrics such as precision and recall. The proposed system achieved a high accuracy of 97% while detecting and recognizing real-time objects.

With the rapid development of autonomous driving, real-time object detection on 360° images becomes more and more important. In this paper, we propose a panoramic virtual dataset for training object detectors on 360° images. The most important feature of our dataset includes (1) an auto-generated city scene is created for rendering 360° dataset. (2) annotation work for this dataset is automatic. In addition, we propose a modified YOLOv3 model called Pano-YOLO for real-time panoramic object detection. Compared with YOLOv3, mAP of Pano-YOLO drops 0.39%. While speed is 32.47% faster. Experiments are performed to show that models trained on our virtual dataset can be applied in real world. And Pano-YOLO is capable of real-time object detection task on high-resolution 360° panoramic images and videos.

Real-time object detection and ranging of multiple objects on the road are the essential tasks in the field of autonomous driving. In this paper, we introduce a system for simultaneous detection and ranging of vehicles, people, non-motor vehicles and lanes based on RGB-D images. Among them, the detection of vehicles, people and non-motor vehicles belongs to general detection task and the lane detection belongs to segmentation task. In order to improve the accuracy and speed, we use two networks to complete these two tasks. We propose a real-time synchronization method with multi-GPU, which achieves separate training and simultaneous detection of lane detectior and vehicle, people and non-motor vehicle detector. We also propose a center-selective ranging module based on binocular ranging technology to distance the detected object. The system reaches nearly 15 FPS with four 1080Ti GPUs. We construct datasets about these problems including daytime and night in which the system achieves high accuracy. A real-time test of the system on the streets of Tianjin, China has been conducted by us, it has proved that the system can be applied to actual driving.

In recent years, 3D object detection has attracted considerable interest from researchers due to its crucial importance in scene understanding tasks for mobile robots. The task of 3D object detection is to determine the position, orientation, scale, and category of objects in a scene, with multimodal data inputs. These inputs consist of two distinct types: images and point clouds. Images provide colour information about the scene, while point clouds deliver geometric information. The fusion of these two diverse data types can enhance the detection of 3D objects by allowing them to complement each other. In this paper, a review of real-time multimodal 3D object detection from the perspective of multimodal sensor fusion is presented. It is important to note that previous reviews of multimodal 3D object detection have been limited to autonomous driving scenarios. In contrast, this paper reviews multimodal 3D object detection approaches in both indoor and outdoor scenarios. In addition, the popular datasets and assessment metrics employed for 3D object detection are described, as well as the issues and future prospects of 3D object detection.

Thanks to the maturity of their field, Unmanned Aerial Vehicles (UAVs) have a wide range of applications. Recently, we have witnessed an increase in the usage of multiple UAVs and UAV swarm due to their ability to achieve more complex tasks. Our goal is to use deep learning methods for object detection in order to detect and track a target drone in an image captured by another drone. In this work, we review four popular object detection categories: two-stage (anchor-based) methods, one-stage (anchor-based) methods, anchor free methods and Transformer-based methods. We compare these methods’ performance (COCO benchmark) and detection speed (FPS) for the task of real-time monocular 2D object detection between dual drones. We created a new dataset using footage from different scenes such as cities, villages, forests, highways, and factories. In our dataset, drone target bounding boxes are present at multiple scales. Our experiments show that anchor free and Transformer-based methods have the best performance. As for detection speed, the one-stage methods obtain the best results followed by and anchor free methods.

Object detection and tracking are two critical tasks in computer vision, widely applied in security surveillance, autonomous vehicles, and behavioral analysis. Strong performance in object detection has been demonstrated by recent Transformer-based models, such as RT-DETR (Real-Time Detection Transformer), due to their global context modeling and high accuracy. However, an inherent tracking mechanism is lacking in RT-DETR, which requires additional components to maintain identity consistency across frames. To address this limitation, an integration of RT-DETR with DeepSORT is proposed, leveraging the strengths of both models to enhance real-time object detection and tracking. A comparative evaluation with YOLOv8, a widely used real-time detector, is conducted to highlight the advantages of the proposed approach in tracking accuracy and robustness. Experiments show that effective performance is achieved in challenging scenarios such as object occlusion and intersection. Specifically, an IDF1 score of 60.0%, a MOTA of 42.4%, and a MOTP of 43.3% are obtained by RTl+DeepSORT on the MOT17-02-DPM dataset, outperforming YOLOv8x+DeepSORT. These results indicate that significant improvements in tracking accuracy are attained while real-time efficiency is maintained, making the proposed approach well-suited for applications such as intelligent surveillance and autonomous navigation.

Cloud computing infrastructures have become the de-facto platform for data driven machine learning applications. However, these centralized models of computing are unqualified for dispersed high-volume real-time edge data intensive applications such as real time object detection, where video streams may be captured at multiple geographical locations. While many recent advancements in object detection have been made using Convolutional Neural Networks, these performance improvements only focus on a single, contiguous object detection model. In this paper, we propose a distributed Edge-Cloud R-CNN pipeline. By splitting the object detection pipeline into components and dynamically distributing these components in the cloud, we can achieve optimal performance to enable real time object detection. As a proof of concept, we evaluate the performance of the proposed system on a distributed computing platform including cloud servers and edge-embedded devices for real-time object detection on live video streams.

Deep convolutional neural network (DCNN) based computer vision methods have great progress in object detection tasks. And object detection is essential to many applications such as autonomous robots and vehicles. However, it is difficult for object detection system to be deployed on embedded platforms due to its intensive computing architecture. We present an object detector MobileNet-SSD which can be deployed on embedded platforms. The object detector presented in this work based on Single Shot Detector (SSD) framework and replace the feature extractor with a more light weight network MobileNetV1. General matrix to matrix multiplication is used to simplify the calculation of convolution operation and is further optimized using ARM NEON technology. Finally, the object detector MobileNet-SSD is deployed on embedded platform and achieves 1.13FPS with 0.72 mean average precision on PASCAL VOC dataset.