scholarly journals Semi-Autonomous Learning Algorithm for Remote Image Object Detection Based on Aggregation Area Instance Refinement

2021 ◽  
Vol 13 (24) ◽  
pp. 5065
Author(s):  
Bei Cheng ◽  
Zhengzhou Li ◽  
Hui Li ◽  
Zhiquan Ding ◽  
Tianqi Qin
Keyword(s):  
Object Detection ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Autonomous Learning ◽  
Region Merging ◽  
Residual Network ◽  
High Quality ◽  
Association Coefficient ◽  
Image Object Detection ◽  
Image Object

Semi-autonomous learning for object detection has attracted more and more attention in recent years, which usually tends to find only one object instance with the highest score in each image. However, this strategy usually highlights the most representative part of the object instead of the whole object, which may lead to the loss of a lot of important information. To solve this problem, a novel end-to-end aggregate-guided semi-autonomous learning residual network is proposed to perform object detection. Firstly, a progressive modified residual network (MRN) is applied to the backbone network to make the detector more sensitive to the boundary features of the object. Then, an aggregate-based region-merging strategy (ARMS) is designed to select high-quality instances by selecting aggregation areas and merging these regions. The ARMS selects the aggregation areas that are highly related to the object through association coefficient, and then evaluates the aggregation areas through a similarity coefficient and fuses them to obtain high-quality object instance areas. Finally, a regression-locating branch is further developed to refine the location of the object, which can be optimized jointly with regional classification. Extensive experiments demonstrate that the proposed method is superior to state-of-the-art methods.

scholarly journals A Region-Based Efficient Network for Accurate Object Detection

2021 ◽  
Vol 38 (2) ◽  
pp. 481-494
Author(s):  
Yurong Guan ◽  
Muhammad Aamir ◽  
Zhihua Hu ◽  
Waheed Ahmed Abro ◽  
Ziaur Rahman ◽  
...  
Keyword(s):  
Object Detection ◽  
Detection Efficiency ◽  
Visual Object ◽  
Average Precision ◽  
High Quality ◽  
Image Objects ◽  
Object Proposal ◽  
Proposed Model ◽  
Image Object Detection ◽  
Image Object

Object detection in images is an important task in image processing and computer vision. Many approaches are available for object detection. For example, there are numerous algorithms for object positioning and classification in images. However, the current methods perform poorly and lack experimental verification. Thus, it is a fascinating and challenging issue to position and classify image objects. Drawing on the recent advances in image object detection, this paper develops a region-baed efficient network for accurate object detection in images. To improve the overall detection performance, image object detection was treated as a twofold problem, involving object proposal generation and object classification. First, a framework was designed to generate high-quality, class-independent, accurate proposals. Then, these proposals, together with their input images, were imported to our network to learn convolutional features. To boost detection efficiency, the number of proposals was reduced by a network refinement module, leaving only a few eligible candidate proposals. After that, the refined candidate proposals were loaded into the detection module to classify the objects. The proposed model was tested on the test set of the famous PASCAL Visual Object Classes Challenge 2007 (VOC2007). The results clearly demonstrate that our model achieved robust overall detection efficiency over existing approaches using fewer or more proposals, in terms of recall, mean average best overlap (MABO), and mean average precision (mAP).

scholarly journals Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3415 ◽  
Author(s):  
Jinpeng Zhang ◽  
Jinming Zhang ◽  
Shan Yu
Keyword(s):  
Object Detection ◽  
Sampling Method ◽  
Ground Truth ◽  
Detection Accuracy ◽  
Two Stage ◽  
Baseline Model ◽  
Detection Algorithms ◽  
Imbalance Problem ◽  
Image Object Detection ◽  
Image Object

In the image object detection task, a huge number of candidate boxes are generated to match with a relatively very small amount of ground-truth boxes, and through this method the learning samples can be created. But in fact the vast majority of the candidate boxes do not contain valid object instances and should be recognized and rejected during the training and evaluation of the network. This leads to extra high computation burden and a serious imbalance problem between object and none-object samples, thereby impeding the algorithm’s performance. Here we propose a new heuristic sampling method to generate candidate boxes for two-stage detection algorithms. It is generally applicable to the current two-stage detection algorithms to improve their detection performance. Experiments on COCO dataset showed that, relative to the baseline model, this new method could significantly increase the detection accuracy and efficiency.

Image object detection and semantic segmentation based on convolutional neural network

2019 ◽  
Vol 32 (7) ◽  
pp. 1949-1958 ◽  
Author(s):  
Laigang Zhang ◽  
Zhou Sheng ◽  
Yibin Li ◽  
Qun Sun ◽  
Ying Zhao ◽  
...  
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Semantic Segmentation ◽  
Image Object Detection ◽  
Image Object

scholarly journals Defect-Detection Model for Underground Parking Lots Using Image Object-Detection Method

2021 ◽  
Vol 66 (3) ◽  
pp. 2493-2507
Author(s):  
Hyun Kyu Shin ◽  
Si Woon Lee ◽  
Goo Pyo Hong ◽  
Sael Lee ◽  
Sang Hyo Lee ◽  
...  
Keyword(s):  
Object Detection ◽  
Defect Detection ◽  
Detection Method ◽  
Parking Lots ◽  
Detection Model ◽  
Image Object Detection ◽  
Image Object

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 Still Face Image Object Detection using EV-Jones Algorithm

2017 ◽  
Vol 179 (1) ◽  
pp. 34-38
Author(s):  
Gogineni Rajesh ◽  
Kolasani Ramchand ◽  
V. V.
Keyword(s):  
Object Detection ◽  
Face Image ◽  
Image Object Detection ◽  
Image Object
Sign in / Sign up

Export Citation Format

Share Document