YOLO-DSD: A YOLO-Based Detector Optimized for Better Balance between Accuracy, Deployability and Inference Time in Optical Remote Sensing Object Detection
نویسندگان
چکیده
Many deep learning (DL)-based detectors have been developed for optical remote sensing object detection in recent years. However, most of the are toward pursuit a higher accuracy, but little balance between deployability and inference time, which hinders practical application these detectors, especially embedded devices. In order to achieve accuracy reduce computational consumption time simultaneously, novel convolutional network named YOLO-DSD was based on YOLOv4. Firstly, new feature extraction module, dense residual (DenseRes) block, proposed backbone by utilizing series-connected structure with same topology improving while reducing time. Secondly, convolution layer–batch normalization layer–leaky ReLu (CBL) ×5 modules neck, S-CBL×5, were improved short-cut connection mitigate loss. Finally, low-cost attention mechanism called dual channel (DCA) block introduced each S-CBL×5 better representation features. The experimental results DIOR dataset indicate that outperforms YOLOv4 increasing mAP0.5 from 71.3% 73.0%, 23.9% 29.7% reduction Params Flops, respectively, 50.2% improvement FPS. RSOD dataset, is increased 90.0~94.0% 92.6~95.5% under different input sizes. Compared SOTA achieves
منابع مشابه
Complex-YOLO: Real-time 3D Object Detection on Point Clouds
Lidar based 3D object detection is inevitable for autonomous driving, because it directly links to environmental understanding and therefore builds the base for prediction and motion planning. The capacity of inferencing highly sparse 3D data in real-time is an ill-posed problem for lots of other application areas besides automated vehicles, e.g. augmented reality, personal robotics or industri...
متن کاملA Robust Real-Time Automatic License Plate Recognition based on the YOLO Detector
Automatic License Plate Recognition (ALPR) has been a frequent topic of research due to many practical applications. However, many of the current solutions are still not robust in real-world situations, commonly depending on many constraints. This paper presents a robust and efficient ALPR system based on the state-of-the-art YOLO object detector. The Convolutional Neural Networks (CNNs) are tr...
متن کاملFast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video
Object detection is considered one of the most challenging problems in this field of computer vision, as it involves the combination of object classification and object localization within a scene. Recently, deep neural networks (DNNs) have been demonstrated to achieve superior object detection performance compared to other approaches, with YOLOv2 (an improved You Only Look Oncemodel) being one...
متن کاملA Survey on Object Detection in Optical Remote Sensing Images
Object detection in optical remote sensing images, being a fundamental but challenging problem in the field of aerial and satellite image analysis, plays an important role for a wide range of applications and is receiving significant attention in recent years. While enormous methods exist, a deep review of the literature concerning generic object detection is still lacking. This paper aims to p...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Applied sciences
سال: 2022
ISSN: ['2076-3417']
DOI: https://doi.org/10.3390/app12157622