CPU Based YOLO: A Real Time Object Detection Algorithm

Deep neural networks (DNNs) play an important role in our daily lives, from aiding us in menial tasks to solving world issues such as cancer cell detection. However, few pieces of research have been conducted using DNNs and deep learning models as a medium to help classify and detect trash, in efforts to solve our global waste crisis. This is because current DNNs struggle to be both efficient and accurate while detecting indistinct objects such as waste. To address this issue, this work focuses on YOLO-Green, a novel real-time object detection model designed specifically for trash detection. The model is trained on a dataset gathered from real-world trash divided into seven of the most common types of solid waste. With only 100 epochs of training, YOLO-Green achieves an outstanding mAP of 78.04%, FPS of 2.72, while retaining a model size of only 117 MB. Based on the original object detection of YOLOv4, YOLO-Green exceeds YOLOv4 and other popular deep learning models in both its accuracy and efficiency, while maintaining a relatively small model size. Ultimately, this study sheds a positive light on the potential of using deep learning models as an alternative to manual waste management.

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.

Today, Computer Vision is one of the most well-liked and critical research areas in the Computer Science field. Moving object detection is the first and foremost step in any computer vision applications. The detection of moving object in any computer vision application is a very critical task. The most widely used method for moving object detection is Frame differencing based background subtraction method. The most of the researchers address the various challenges of background subtraction algorithm to detect the object accurately, the segmentation of objects from non stationary objects is critical, adaptation of illumination changes and handling of camouflage and etc. But they are more CPU and I/O intensive one. Cloud Computing is the new buzz word in computer field which provides computational power on demand basis which requires the representation of e-science workflow model for such kind of large-scale scientific applications. There are four different types of scientific work flow models viz Montage, LIGO, SIPHT, and Cybershake are exist which are varied by either CPU intensive or I/O intensive application. But the Temporal frame differencing based real time object detection is both CPU and I/O intensive one. Hence which could not be expresses as a single workflow model for cloud computing. So, we proposed a hybrid workflow model (Montage and SIPHT) of temporal frame differencing algorithm for real time object detection and the performance of such workflow model is tested and analyzed in already existing scheduling algorithm in workflowsim.

Over the past few years, deep learning has played a tremendous role in real time object detection, recognition and classification. Today, algorithms use deep learning not only for simple object detection but have also paved way for vehicle detection that is complex situation such as Indian roads. Different deep learning models can learn features of varied complexity and perform according to surrounding environment in which they are deployed. In this paper a comparison of six models is performed for detection of vehicles on roads that are unstructured or unconstrained. Till date, deep learning algorithms are being used for vehicle (car, bus, truck, motorcycle etc.) detection. A dataset based on Indian road scenario has been used for training on models: faster RCNN and Single Shot Detector (SSD) combined with convolution classifiers mobilenet, resnet and inceptionnet. The six models are compared by evaluating mean average precision (mAP) and classification time complexity for IDD dataset. The observations suggested faster RCNN Resnet50 resolves the trade-off of time and accuracy. Whereas SSD mobilenet V1 takes 31.89% less time than faster RCNN resnet101. On the flipped side, faster RCNN resnet101is 34.38% more accurate than SSD mobilenet v1.

As Smartphone is getting more potent, can do more superior stuffs that previous required a computer. For employing the high processing power of Smartphone is mobile computer vision, the ability for a device to capture; process; analyze; understanding of images. For mobile computer vision, Smartphone must be faster and real time. In this study two applications have been developed on Android platform using OpenCV and core library called as CamTest with own implemented algorithms. Efficiency of two Android applications have been compared and found that OpenCV performs faster than CamTest. The results of examining the best object detection algorithm with reverence to efficiency shows that FAST algorithm has the finest blend of speed and object detection performance. Next projected object recognition system using FAST algorithm, which uses SVM, BPNN for training and validation of object in real time. The application detects the object perfectly with recognition time around 2 ms using SVM and 1 ms using BPNN.

Object Detection has been one of the areas of interest of research community for over years and has made significant advances in its journey so far. There is a tremendous scope in the applications that would benefit with more innovations in the domain of object detection. Rapid growth in the field of machine learning has complemented the efforts in this area and in the recent times, research community has contributed a lot in real time object detection. In the current work, authors have implemented real time object detection and have made efforts to improve the accuracy of the detection mechanism. In the current research, we have used ssd_v2_inception_coco model as Single Shot Detection models deliver significantly better results. A dataset of more than 100 raw images is used for training and then xml files are generated using labellimg. Tensor flow records generated are passed through training pipelines using the proposed model. OpenCV captures real-time images and CNN performs convolution operations on images. The real time object detection delivers an accuracy of 92.7%, which is an improvement over some of the existing models already proposed earlier. Model detects hundreds of objects simultaneously. In the proposed model, accuracy of object detection significantly improvises over existing methodologies in practice. There is a substantial dataset to evaluate the accuracy of proposed model. The model may be readily useful for object detection applications including parking lots, human identification, and inventory management.

Basic tasks in computer vision, object detection and localization have many applications in autonomous driving, robotics, surveillance, and healthcare [1]. Deep learning has enabled previously unheard-of levels of accuracy and robustness in object detection and localization tasks, revolutionizing the area in recent years. This paper provides a thorough overview of the most recent developments and approaches in the application of deep learning algorithms for localization and object detection. First, we go over the basic ideas behind object identification and localization, emphasizing the difficulties caused by different item sizes, occlusions, and cluttered backgrounds. We then explore the nuances of deep learning architectures designed specifically for these kinds of tasks: anchor-free approaches like Center Net, single-shot detectors like YOLO, and region-based detectors like Faster R-CNN. We investigate feature extraction networks, object detecting heads, and training procedures for best performance as we investigate the underlying mechanics of these architectures. We also go over important assessment measures and datasets that are necessary for benchmarking and training object detection algorithms. We stress the significance of using strong evaluation techniques to guarantee the dependability and capacity for generalization of the suggested algorithms. Apart from technical concerns, we investigate practical uses cases where object detection and localization are essential, like autonomous vehicle pedestrian identification, surveillance system object tracking, and medical imaging anomaly detection. Lastly, we examine new developments and directions for the discipline, such as integrating multimodal data, handling domain shifts, and improving object detection algorithms' interpretability and fairness. Our goal is to stimulate further developments in computer vision systems by offering scholars, professionals, and hobbyists insightful knowledge about the problems and cutting-edge methods of object recognition and localization through this thorough review. The content of the paper is succinctly summarized in this abstract, which also highlights the significance of deep learning, object detection and localization, important methodology, datasets, applications, and future developments in the field.

Deep learning-based object detection in low-altitude UAV datasets: A survey

Unmanned Aerial Vehicles (UAVs) have gained significant traction for real-time surveillance applications such as object tracking and search-and-rescue missions. A key enabler of these capabilities is the integration of a real-time, highly accurate object detection system. While available two-stage detectors like R-CNN, Fast R-CNN, Faster R-CNN, and Mask R-CNN achieve high detection accuracy and precise localization by dividing the image into regions and classifying each region, they are often slow, complex, and resource-intensive, making them unsuitable for real-time applications. To address this limitation, this research utilizes a Darknet-based YOLOv3 (You Only Look Once, Version 3), a state-of-the-art algorithm for real-time object detection in videos, live feeds, and images. Leveraging a deep Convolutional Neural Network (CNN), YOLOv3 efficiently learns features and predicts object locations and class probabilities in a single pass, ensuring high-speed and reliable detection. A real-time aerial surveillance system for quadcopter application using machine vision is proposed. The training dataset, obtained from the internet and self-taken images from a camera, was manually annotated into three critical categories: suspect, bandit, and weapon. The dataset was subsequently divided into training and testing subsets. Experimental results demonstrate that the proposed system achieves outstanding detection accuracy, with an overall mean average precision (mAP@0.5) of 93.82%, precision of 94%, and recall of 83%. Compared to a ResNet-50-based Faster R-CNN model, the YOLOv3-based approach outperformed, achieving success rates of 0.81 for the Bandit class and 1.00 for both Suspect and Weapon classes. This research improves drone-based AI for real-time object detection in security systems, enhancing efficiency and adaptability. It also creates specialized datasets, including a tailored bandit dataset, to support future UAV security research.

Object detection is not only shaping how Computers see and analyze things but it is also helping in the behavior of how an object reacts to the change in its environment. The main application of these object detection sensors or software is to find the location of an object in space or to track its movement. Object detection has infinitely many use cases and in this paper, we are introducing an application that will allow safety of users struck in a disaster and who need to be evacuated. In such cases the main thing to focus and to eradicate is camera noise, saturation and image compression. Our solution is to establish a connection between the person struck in a disaster with fire safety people. This works over a convolutional network that allows us to detect vulnerable things present inside a room that needs to be rescued and can also give an insight of any explosive inside the room. Our model uses Faster-RCNN and COCO which is a pretrained dataset. This allows real time object detection and classification on our network. Using this we were able to detect an object or a person and get him to rescue by providing them a shortest way out of that place. With this we were able to get an accuracy of more than 75% in our object detection model.

The paper presents review of key aspects associated with object detection and tracking algorithms in sensing systems for automotive applications covering active safety, advanced driver assistance and autonomous driving systems. The role of discussed systems is to establish location and monitor relative movement of objects and environment with main focus on identification of vulnerable road users. The object detection algorithms allow to classify and differentiate both static and dynamic objects in the vehicle’s surrounding. The analysis will be focused on selection of most suitable platform for development of optimized and safe vulnerable road user detection system.

Rapid advancement of computer vision technologies has led to significant progress in the field of object detection, with applications ranging from surveillance to autonomous vehicles. One critical application is the identification of weapons in real-time scenarios, such as security monitoring and law enforcement. This paper presents a novel approach for weapon identification using the YOLOv5 (You Only Look Once version 5) algorithm, a state-of-the-art real-time object detection model. Traditional methods of weapon identification often rely on manual intervention or limited rule-based systems, which can be time-consuming and prone to errors. In contrast, the proposed method harnesses the power of deep learning to automate the detection process. YOLOv5, known for its speed and accuracy, is employed to detect and classify weapons in images and video streams. The dataset used for training encompasses a diverse range of weapon types, orientations, and lighting conditions to ensure robustness. The methodology involves fine-tuning the YOLOv5 architecture on the weapon dataset, optimizing hyperparameters, and leveraging data augmentation techniques to improve model generalization. The resulting trained model demonstrates remarkable proficiency in real-time weapon detection, outperforming traditional methods and achieving high precision and recall rates. Experimental results on benchmark datasets and custom video sequences showcase the effectiveness of the proposed approach. The YOLOv5-based weapon identification system exhibits the capability to swiftly and accurately detect weapons, thus holding significant promise for enhancing security measures in public spaces, transportation hubs, and high-security areas. In conclusion, this paper contributes to the domain of automated security systems by introducing a robust and efficient solution for weapon identification. The utilization of YOLOv5 demonstrates the potential of deep learning to address critical real-world challenges, paving the way for safer environments through advanced object detection techniques.

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.

With the increasing aging of the population, the design of automatic bath robot has the forward-looking significance. The robot needs to detect the skin position, so as to perform the bathing task. The perception of skin is the key technology to achieve the bathing task. In this paper, object detection is used to identify the skin, which provides reference information for the pose of the robot. According to the classification of the object detection algorithms, this paper selects four typical object detection algorithms, namely, Faster R-CNN, YOLOv3, YOLOv4 and CenterNet. Due to the limitation of the self-built data set, this paper adopts the transfer learning to promote the completion of new tasks, which takes the pre-trained model as the starting point. The experimental results show that the detection results of YOLOv4 is the best, with mAP of 78%. This paper proves the feasibility and effectiveness of object detection completing the human skin detection in the bathing task.

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.