SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network

2018 ◽  
pp. 210-226 ◽  
Author(s):  
Yancheng Bai ◽  
Yongqiang Zhang ◽  
Mingli Ding ◽  
Bernard Ghanem
Keyword(s):  
Object Detection ◽  
Small Object ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Small Object Detection

scholarly journals Centered Multi-Task Generative Adversarial Network for Small Object Detection

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 5194
Author(s):  
Hongfeng Wang ◽  
Jianzhong Wang ◽  
Kemeng Bai ◽  
Yong Sun
Keyword(s):  
Object Detection ◽  
Super Resolution ◽  
Small Object ◽  
Gaze Estimation ◽  
Two Stage ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Image Super Resolution ◽  
Small Object Detection ◽  
Original Feature

Despite the breakthroughs in accuracy and efficiency of object detection using deep neural networks, the performance of small object detection is far from satisfactory. Gaze estimation has developed significantly due to the development of visual sensors. Combining object detection with gaze estimation can significantly improve the performance of small object detection. This paper presents a centered multi-task generative adversarial network (CMTGAN), which combines small object detection and gaze estimation. To achieve this, we propose a generative adversarial network (GAN) capable of image super-resolution and two-stage small object detection. We exploit a generator in CMTGAN for image super-resolution and a discriminator for object detection. We introduce an artificial texture loss into the generator to retain the original feature of small objects. We also use a centered mask in the generator to make the network focus on the central part of images where small objects are more likely to appear in our method. We propose a discriminator with detection loss for two-stage small object detection, which can be adapted to other GANs for object detection. Compared with existing interpolation methods, the super-resolution images generated by CMTGAN are more explicit and contain more information. Experiments show that our method exhibits a better detection performance than mainstream methods.

scholarly journals Small Object Detection in Remote Sensing Images Based on Super-Resolution with Auxiliary Generative Adversarial Networks

2020 ◽  
Vol 12 (19) ◽  
pp. 3152
Author(s):  
Luc Courtrai ◽  
Minh-Tan Pham ◽  
Sébastien Lefèvre
Keyword(s):  
Remote Sensing ◽  
Object Detection ◽  
Network Architecture ◽  
Super Resolution ◽  
Remote Sensing Data ◽  
Generative Adversarial Networks ◽  
Small Object ◽  
Remote Sensing Images ◽  
Generative Adversarial Network ◽  
Small Object Detection

This article tackles the problem of detecting small objects in satellite or aerial remote sensing images by relying on super-resolution to increase image spatial resolution, thus the size and details of objects to be detected. We show how to improve the super-resolution framework starting from the learning of a generative adversarial network (GAN) based on residual blocks and then its integration into a cycle model. Furthermore, by adding to the framework an auxiliary network tailored for object detection, we considerably improve the learning and the quality of our final super-resolution architecture, and more importantly increase the object detection performance. Besides the improvement dedicated to the network architecture, we also focus on the training of super-resolution on target objects, leading to an object-focused approach. Furthermore, the proposed strategies do not depend on the choice of a baseline super-resolution framework, hence could be adopted for current and future state-of-the-art models. Our experimental study on small vehicle detection in remote sensing data conducted on both aerial and satellite images (i.e., ISPRS Potsdam and xView datasets) confirms the effectiveness of the improved super-resolution methods to assist with the small object detection tasks.

scholarly journals Optimization of Small Object detection based on Generative Adversarial Networks

2021 ◽  
Vol 245 ◽  
pp. 03062
Author(s):  
Zhang Ruiqiang ◽  
Zeng Yu ◽  
Jin Xin
Keyword(s):  
Object Detection ◽  
Computational Cost ◽  
Multiple Scale ◽  
Input Image ◽  
Generative Adversarial Networks ◽  
Small Object ◽  
Generative Adversarial Network ◽  
Detection Techniques ◽  
Low Efficiency ◽  
Small Object Detection

Small object detection is one of the fundamental problems in computer vision applications. Existing small object detection techniques usually focus on detecting small objects with multiple scale of features with low efficiency due to high computational cost. In this paper, we investigate small object detection problem based on generative adversarial architecture that utilizes features of small objects. We propose an Optimized Perceptual Generative Adversarial Network (OPGAN) to present more features of small objects. Specifically, the generator of OPGAN learns to present the low-resolution features of the small objects to highly resolved features similar to large objects as input image of the discriminator model. After then, the discriminator of OPGAN computes the generated feature and generates a new perceptual requirement parameter into the model to train the model iteratively. Extensive experiments on the challenging benchmark data sets demonstrate the effectiveness of OPGAN in detecting small objects.

A Study of an X-band FMCW Radar for Small Object Detection

2021 ◽  
Author(s):  
Tripop Tongboonsong ◽  
Akkarat Boonpoonga ◽  
Kittisak Phaebua ◽  
Titipong Lertwiriyaprapa ◽  
Lakkhana Bannawat
Keyword(s):  
Object Detection ◽  
Small Object ◽  
Fmcw Radar ◽  
X Band ◽  
Small Object Detection

Realize Your Surroundings: Exploiting Context Information for Small Object Detection

2021 ◽  
Author(s):  
Jiaxu Leng ◽  
Yihui Ren ◽  
Wen Jiang ◽  
Xiaoding Sun ◽  
Ye Wang
Keyword(s):  
Object Detection ◽  
Context Information ◽  
Small Object ◽  
Small Object Detection
Sign in / Sign up

Export Citation Format

Share Document