scholarly journals A Complex Valued ResNet Network Based Object Detection Algorithm in SAR Images

2021 ◽  
Vol 24 (4) ◽  
pp. 392-400
Author(s):  
Insu Hwang
Keyword(s):  
Object Detection ◽  
Detection Algorithm ◽  
Aerial Image ◽  
Complex Data ◽  
Sar Image ◽  
Sar Images ◽  
Phase Data ◽  
Image Object Detection ◽  
Complex Valued ◽  
Image Object

Unlike optical equipment, SAR(Synthetic Aperture Radar) has the advantage of obtaining images in all weather, and object detection in SAR images is an important issue. Generally, deep learning-based object detection was mainly performed in real-valued network using only amplitude of SAR image. Since the SAR image is complex data consist of amplitude and phase data, a complex-valued network is required. In this paper, a complex-valued ResNet network is proposed. SAR image object detection was performed by combining the ROI transformer detector specialized for aerial image detection and the proposed complex-valued ResNet. It was confirmed that higher accuracy was obtained in complex-valued network than in existing real-valued network.

scholarly journals Target Detection of UAV Aerial Image Based on Rotational Invariant Depth Denoising Automatic Encoder

2020 ◽  
Vol 38 (6) ◽  
pp. 1345-1351
Author(s):  
Fengping Yang ◽  
Bodi Ma ◽  
Jinrong Wang ◽  
Honggang Gao ◽  
Zhenbao Liu
Keyword(s):  
Object Detection ◽  
Target Detection ◽  
Traffic Monitoring ◽  
Aerial Image ◽  
Feature Descriptor ◽  
Rotation Invariant ◽  
Regional Survey ◽  
Radial Gradient ◽  
Image Object Detection ◽  
Image Object

The method of using unmanned aerial vehicle (UAV) to obtain aerial image information of target scene has the characteristics of wide coverage, strong mobility and high efficiency, which is widely used in urban traffic monitoring, vehicle detection, oil pipeline inspection, regional survey and other aspects. Aiming at the difficulties of the object to be detected in the process of aerial image object detection, such as multiple orientations, small image pixel size and UAV body vibration interference, a novel aerial image object detection model based on the rotation-invariant deep denoising auto encoder is proposed in this paper. Firstly, the interest region of the aerial image is extracted by the selective search method, and the radial gradient of interest region is calculated. Then, the rotation invariant feature descriptor is obtained from the radial gradient feature, and the noise in the original data is filtered out by the deep denoising automatic encoder and the deep feature of the feature descriptors is extracted. Finally, the experimental results show that this method can achieve high accuracy for aerial image target detection and has good rotation invariance.

scholarly journals Improving the precision and accuracy of animal population estimates with aerial image object detection

2019 ◽  
Vol 10 (11) ◽  
pp. 1875-1887 ◽  
Author(s):  
Jasper A. J. Eikelboom ◽  
Johan Wind ◽  
Eline van de Ven ◽  
Lekishon M. Kenana ◽  
Bradley Schroder ◽  
...  
Keyword(s):  
Object Detection ◽  
Aerial Image ◽  
Population Estimates ◽  
Animal Population ◽  
Precision And Accuracy ◽  
Image Object Detection ◽  
Image Object

Aerial Image Object Detection Method Based on Adaptive ClusDet Network

2021 ◽  
Author(s):  
Zhitian Li ◽  
Shanlin Sun ◽  
Yun Li ◽  
Biaohang Sun ◽  
Kai Tian ◽  
...  
Keyword(s):  
Object Detection ◽  
Detection Method ◽  
Aerial Image ◽  
Image Object Detection ◽  
Image Object

Aerial Image Object Detection Based on Superpixel-Related Patch

2021 ◽  
pp. 256-268
Author(s):  
Jiehua Lin ◽  
Yan Zhao ◽  
Shigang Wang ◽  
Meimei Chen ◽  
Hongbo Lin ◽  
...  
Keyword(s):  
Object Detection ◽  
Aerial Image ◽  
Image Object Detection ◽  
Image Object

scholarly journals Dual-NMS: A Method for Autonomously Removing False Detection Boxes from Aerial Image Object Detection Results

Sensors ◽  
2019 ◽  
Vol 19 (21) ◽  
pp. 4691 ◽  
Author(s):  
Lin ◽  
Wu ◽  
Fu ◽  
Wang ◽  
Zhang ◽  
...  
Keyword(s):  
Object Detection ◽  
Removal Rate ◽  
Aerial Images ◽  
Aerial Image ◽  
Post Processing ◽  
False Detection ◽  
Channel Separation ◽  
Image Object Detection ◽  
Image Object ◽  
Detection Effect

In the field of aerial image object detection based on deep learning, it’s difficult to extract features because the images are obtained from a top-down perspective. Therefore, there are numerous false detection boxes. The existing post-processing methods mainly remove overlapped detection boxes, but it’s hard to eliminate false detection boxes. The proposed dual non-maximum suppression (dual-NMS) combines the density of detection boxes that are generated for each detected object with the corresponding classification confidence to autonomously remove the false detection boxes. With the dual-NMS as a post-processing method, the precision is greatly improved under the premise of keeping recall unchanged. In vehicle detection in aerial imagery (VEDAI) and dataset for object detection in aerial images (DOTA) datasets, the removal rate of false detection boxes is over 50%. Additionally, according to the characteristics of aerial images, the correlation calculation layer for feature channel separation and the dilated convolution guidance structure are proposed to enhance the feature extraction ability of the network, and these structures constitute the correlation network (CorrNet). Compared with you only look once (YOLOv3), the mean average precision (mAP) of the CorrNet for DOTA increased by 9.78%. Commingled with dual-NMS, the detection effect in aerial images is significantly improved.

Sign in / Sign up

Export Citation Format

Share Document