Efficient Object Detection Model for Real-Time UAV Applications (original) (raw)
Related papers
Efficient Object Detection Model for Real-time UAV Application
Computer and Information Science, 2021
Unmanned Aerial Vehicles (UAVs) equipped with vision capabilities have become popular in recent years. Many applications have especially been employed object detection techniques extracted from the information captured by an onboard camera. However, object detection on UAVs requires high performance, which has a negative effect on the result. In this article, we propose a deep feature pyramid architecture with a modified focal loss function, which enables it to reduce the class imbalance. Moreover, the proposed method employed an end to end object detection model running on the UAV platform for real-time application. To evaluate the proposed architecture, we combined our model with Resnet and MobileNet as a backend network, and we compared it with RetinaNet and HAL-RetinaNet. Our model produced a performance of 30.6 mAP with an inference time of 14 fps. This result shows that our proposed model outperformed RetinaNet by 6.2 mAP.
Fast Object Detection for Quadcopter Drone Using Deep Learning
2018 3rd International Conference on Computer and Communication Systems (ICCCS)
The paper presents our research progress in the development of object detection using deep learning based on drone camera. The grand purpose of our research is to deliver important medical aids for patients in emergency situations. The case can be simplified into delivery of an item from start to the goal position. We will exploit the drone technology for transporting items efficiently. In sending process, our drone must detect the object target, where the items will be delivered. Therefore, we need object detection module that can detect what is in video stream and where the object is by using GPS as well. To implement the module, we use combination of MobileNet and the Single Shot Detector (SSD) framework for fast and efficient deep learning-based method to object detection. The ability of deep learning to detect and localize specific objects is studied by conducting experiments using drone camera and, as comparison, using stereo camera Minoru.
On-Board Small-Scale Object Detection for Unmanned Aerial Vehicles (UAVs)
Drones
Object detection is a critical task that becomes difficult when dealing with onboard detection using aerial images and computer vision technique. The main challenges with aerial images are small target sizes, low resolution, occlusion, attitude, and scale variations, which affect the performance of many object detectors. The accuracy of the detection and the efficiency of the inference are always trade-offs. We modified the architecture of CenterNet and used different CNN-based backbones of ResNet18, ResNet34, ResNet50, ResNet101, ResNet152, Res2Net50, Res2Net101, DLA-34, and hourglass14. A comparison of the modified CenterNet with nine CNN-based backbones is conducted and validated using three challenging datasets, i.e., VisDrone, Stanford Drone dataset (SSD), and AU-AIR. We also implemented well-known off-the-shelf object detectors, i.e., YoloV1 to YoloV7, SSD-MobileNet-V2, and Faster RCNN. The proposed approach and state-of-the-art object detectors are optimized and then implemen...
Improved Object Detection in UAV Images using Deep Learning
Cognizance Journal of Multidisciplinary Studies (CJMS), 2024
The use of unmanned aerial vehicles (UAV) for computer vision analysis is a significant trend in the current scenario. UAV technology is highly utilized for various purposes, including object detection, tracking, traffic management, environment monitoring, and agriculture sector, mainly due to the ease of data collection compared to conventional remote sensing methods through satellites. This study focuses on enhancing the YOLOv5 architecture to effectively detect small targets. The modifications made to the YOLOv5 framework specifically target the architecture, resulting in improved performance in object identification. The addition of a new feature fusion layer within the feature pyramid section of YOLOv5 plays a crucial role in achieving these improvements. To maintain resolution and prevent the loss of valuable feature information in the deeper sections of the network, a lateral connection is introduced, connecting this layer to an earlier part of the network. This addition ensures that crucial details and feature data are preserved throughout the network architecture. Additionally, data augmentation techniques such as image saturation and cropping are employed.
Unmanned aerial vehicles and machine learning for detecting objects in real time
Bulletin of Electrical Engineering and Informatics
An unmanned aerial vehicle (UAV) image recognition system in real-time is proposed in this study. To begin, the you only look once (YOLO) detector has been retrained to better recognize objects in UAV photographs. The trained YOLO detector makes a trade-off between speed and precision in object recognition and localization to account for four typical moving entities caught by UAVs (cars, buses, trucks, and people). An additional 1500 UAV photographs captured by the embedded UAV camera are fed into the YOLO, which uses those probabilities to estimate the bounding box for the entire image. When it comes to object detection, the YOLO competes with other deep-learning frameworks such as the faster region convolutional neural network. The proposed system is tested on a wild test set of 1500 UAV photographs with graphics processing unit GPU acceleration, proving that it can distinguish objects in UAV images effectively and consistently in real-time at a detection speed of 60 frames per se...
Object Detection for Unmanned Aerial Vehicle Camera via Convolutional Neural Networks
IEEE journal on miniaturization for air and space systems, 2021
The object tracking alongside the image segmentation have recently become of particular significance in satellite and aerial imagery. The latest achievements in this field are closely related to the application of the deep-learning algorithms and, particularly, convolutional neural networks (CNNs). Supplemented by the sufficient amount of the training data CNNs provide the advantageous performance in comparison to the classical methods based on Viola-Jones or Support vector machines. However, the application of CNNs for the object detection on the aerial images faces several general issues that cause classification error. The first one is related to the limited camera shooting angle and spatial resolution. The second one arises from the restricted dataset for specific classes of objects that rarely appear in the captured data. This paper represents a comparative study on the effectiveness of different deep neural networks for detection of the objects with similar patterns on the images within a limited amount of the pre-trained datasets. It has been revealed that YOLO ver. 3 network enables better accuracy and faster analysis than R-CNN, Fast R-CNN, Faster R-CNN, and SSD architectures. This has been demonstrated on example of "Stanford Dataset", "DOTA v-1.5", and "xView 2018 Detection" datasets. The following metrics on the accuracy have been obtained for the YOLO ver. 3 network: 89.12 mAP (Stanford Dataset), 80.20 mAP (DOTA v-1.5), and 78.29 (xView 2018) for testing; and 85.51 mAP (Stanford Dataset), 79.28 (DOTA v-1.5), and 79.92 (xView 2018) on validation with the analysis speed of 26.82 frames per second.
Car Detection using Unmanned Aerial Vehicles: Comparison between Faster R-CNN and YOLOv3
2019 1st International Conference on Unmanned Vehicle Systems-Oman (UVS), 2019
Unmanned Aerial Vehicles are increasingly being used in surveillance and traffic monitoring thanks to their high mobility and ability to cover areas at different altitudes and locations. One of the major challenges is to use aerial images to accurately detect cars and count-them in real-time for traffic monitoring purposes. Several deep learning techniques were recently proposed based on convolution neural network (CNN) for real-time classification and recognition in computer vision. However, their performance depends on the scenarios where they are used. In this paper, we investigate the performance of two state-of-the art CNN algorithms, namely Faster R-CNN and YOLOv3, in the context of car detection from aerial images. We trained and tested these two models on a large car dataset taken from UAVs. We demonstrated in this paper that YOLOv3 outperforms Faster R-CNN in sensitivity and processing time, although they are comparable in the precision metric.
2019
Unmanned Aerial Vehicles are increasingly beingused in surveillance and traffic monitoring thanks to their highmobility and ability to cover areas at different altitudes andlocations. One of the major challenges is to use aerial imagesto accurately detect cars and count-them in real-time for trafficmonitoring purposes. Several deep learning techniques wererecently proposed based on convolution neural network (CNN)for real-time classification and recognition in computer vision.However, their performance depends on the scenarios wherethey are used. In this paper, we investigate the performance oftwo state-of-the art CNN algorithms, namely Faster R-CNN andYOLOv3, in the context of car detection from aerial images.We trained and tested these two models on a large car datasettaken from UAVs. We demonstrated in this paper that YOLOv3outperforms Faster R-CNN in sensitivity and processing time,although they are comparable in the precision metric. Car Detection using Unmanned Aerial Vehicles...
A Tool to Enhance the Capacity for Deep Learning Based Object Detection and Tracking with Uav Data
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2020
Currently, deployment of UAV has transformed from crucial to day-today scenarios for various purposes such as wastage collection, live entertainment, product delivery, town mapping, etc. Object tracking based UAV applications such as traffic monitoring, wildlife monitoring and surveillance have undergone phenomenal changeover due to deep learning based methodologies. With such transformation, there is also lack of resources to practically explore the UAV images and videos with deep learning methodologies. Hence, a deep learning-based object detection and tracking tool with UAV data (DL-ODT-UAV) is proposed to fill the learning gap, especially among students. DL-ODT-UAV is a resource to acquire basic knowledge about UAV and deep learning based object detection and tracking. It integrates various object annotators, object detectors and object tracker. Single object detection and tracking is performed with YOLO as object detector and LSTM as object tracker. Faster R-CNN is adopted in multiple object detection. With exploring the tool, the ability of students to approach problems related to deep learning methodologies will improve to a greater level.
Convolutional Neural Network-Based Real-Time Object Detection and Tracking for Parrot AR Drone 2
IEEE Access, 2019
Recent advancements in the field of Artificial Intelligence (AI) have provided an opportunity to create autonomous devices, robots, and machines characterized particularly with the ability to make decisions and perform tasks without human mediation. One of these devices, Unmanned Aerial Vehicles (UAVs) or drones are widely used to perform tasks like surveillance, search and rescue, object detection and target tracking, parcel delivery (recently started by Amazon), and many more. The sensitivity in performing said tasks demands that drones must be efficient and reliable. For this, in this paper, an approach to detect and track the target object, moving or still, for a drone is presented. The Parrot AR Drone 2 is used for this application. Convolutional Neural Network (CNN) is used for object detection and target tracking. The object detection results show that CNN detects and classifies object with a high level of accuracy (98%). For real-time tracking, the tracking algorithm responds faster than conventionally used approaches, efficiently tracking the detected object without losing it from sight. The calculations based on several iterations exhibit that the efficiency achieved for target tracking is 96.5%. INDEX TERMS Convolutional neural network, deep learning, object detection, target tracking, unmanned aerial vehicles.