scholarly journals FE-RetinaNet: Small Target Detection with Parallel Multi-Scale Feature Enhancement

Symmetry ◽  
2021 ◽  
Vol 13 (6) ◽  
pp. 950
Author(s):  
Hong Liang ◽  
Junlong Yang ◽  
Mingwen Shao
Keyword(s):  
Target Detection ◽  
Semantic Information ◽  
Detection Accuracy ◽  
Top Down ◽  
Scale Feature ◽  
Feature Enhancement ◽  
Multi Scale ◽  
Feature Pyramid ◽  
Small Targets ◽  
High Level

Because small targets have fewer pixels and carry fewer features, most target detection algorithms cannot effectively use the edge information and semantic information of small targets in the feature map, resulting in low detection accuracy, missed detections, and false detections from time to time. To solve the shortcoming of insufficient information features of small targets in the RetinaNet, this work introduces a parallel-assisted multi-scale feature enhancement module MFEM (Multi-scale Feature Enhancement Model), which uses dilated convolution with different expansion rates to avoid multiple down sampling. MFEM avoids information loss caused by multiple down sampling, and at the same time helps to assist shallow extraction of multi-scale context information. Additionally, this work adopts a backbone network improvement plan specifically designed for target detection tasks, which can effectively save small target information in high-level feature maps. The traditional top-down pyramid structure focuses on transferring high-level semantics from the top to the bottom, and the one-way information flow is not conducive to the detection of small targets. In this work, the auxiliary MFEM branch is combined with RetinaNet to construct a model with a bidirectional feature pyramid network, which can effectively integrate the strong semantic information of the high-level network and high-resolution information regarding the low level. The bidirectional feature pyramid network designed in this work is a symmetrical structure, including a top-down branch and a bottom-up branch, performs the transfer and fusion of strong semantic information and strong resolution information. To prove the effectiveness of the algorithm FE-RetinaNet (Feature Enhancement RetinaNet), this work conducts experiments on the MS COCO. Compared with the original RetinaNet, the improved RetinaNet has achieved a 1.8% improvement in the detection accuracy (mAP) on the MS COCO, and the COCO AP is 36.2%; FE-RetinaNet has a good detection effect on small targets, with APs increased by 3.2%.

scholarly journals Multi-Scale Feature Pyramid Network: A Heavily Occluded Pedestrian Detection Network Based on ResNet

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1820
Author(s):  
Xiaotao Shao ◽  
Qing Wang ◽  
Wei Yang ◽  
Yun Chen ◽  
Yi Xie ◽  
...  
Keyword(s):  
Semantic Information ◽  
Detection System ◽  
Pedestrian Detection ◽  
Detection Accuracy ◽  
The Public ◽  
Scale Feature ◽  
Detection Algorithms ◽  
Multi Scale ◽  
Art Works ◽  
Feature Pyramid

The existing pedestrian detection algorithms cannot effectively extract features of heavily occluded targets which results in lower detection accuracy. To solve the heavy occlusion in crowds, we propose a multi-scale feature pyramid network based on ResNet (MFPN) to enhance the features of occluded targets and improve the detection accuracy. MFPN includes two modules, namely double feature pyramid network (FPN) integrated with ResNet (DFR) and repulsion loss of minimum (RLM). We propose the double FPN which improves the architecture to further enhance the semantic information and contours of occluded pedestrians, and provide a new way for feature extraction of occluded targets. The features extracted by our network can be more separated and clearer, especially those heavily occluded pedestrians. Repulsion loss is introduced to improve the loss function which can keep predicted boxes away from the ground truths of the unrelated targets. Experiments carried out on the public CrowdHuman dataset, we obtain 90.96% AP which yields the best performance, 5.16% AP gains compared to the FPN-ResNet50 baseline. Compared with the state-of-the-art works, the performance of the pedestrian detection system has been boosted with our method.

scholarly journals PFMNet: Few-Shot Segmentation with Query Feature Enhancement and Multi-Scale Feature Matching

Information ◽  
2021 ◽  
Vol 12 (10) ◽  
pp. 406
Author(s):  
Jingyao Li ◽  
Lianglun Cheng ◽  
Zewen Zheng ◽  
Jiahong Chen ◽  
Genping Zhao ◽  
...  
Keyword(s):  
Semantic Information ◽  
Feature Matching ◽  
Semantic Segmentation ◽  
Average Score ◽  
Scale Feature ◽  
Feature Enhancement ◽  
Multi Scale ◽  
Support Set ◽  
Shot Segmentation ◽  
High Level

The datasets in the latest semantic segmentation model often need to be manually labeled for each pixel, which is time-consuming and requires much effort. General models are unable to make better predictions, for new categories of information that have never been seen before, than the few-shot segmentation that has emerged. However, the few-shot segmentation is still faced up with two challenges. One is the inadequate exploration of semantic information conveyed in the high-level features, and the other is the inconsistency of segmenting objects at different scales. To solve these two problems, we have proposed a prior feature matching network (PFMNet). It includes two novel modules: (1) the Query Feature Enhancement Module (QFEM), which makes full use of the high-level semantic information in the support set to enhance the query feature, and (2) the multi-scale feature matching module (MSFMM), which increases the matching probability of multi-scales of objects. Our method achieves an intersection over union average score of 61.3% for one-shot segmentation and 63.4% for five-shot segmentation, which surpasses the state-of-the-art results by 0.5% and 1.5%, respectively.

scholarly journals A New Multiface Target Detection Algorithm for Students in Class Based on Bayesian Optimized YOLOv3 Model

2022 ◽  
Vol 2022 ◽  
pp. 1-12
Author(s):  
Dongmei Shi ◽  
Hongyu Tang
Keyword(s):  
Face Recognition ◽  
Target Detection ◽  
Detection Algorithm ◽  
Bayesian Optimization ◽  
Detection Accuracy ◽  
Small Target ◽  
Sample Distribution ◽  
Feature Pyramid ◽  
Basic Network ◽  
Small Targets

Deep learning theory is widely used in face recognition. Combined with the needs of classroom attendance and students’ learning status monitoring, this article analyzes the YOLO (You Only Look Once) face recognition algorithms based on regression method. Aiming at the problem of small target missing detection in the YOLOv3 network structure, an improved YOLOv3 algorithm based on Bayesian optimization is proposed. The algorithm uses deep separable convolution instead of conventional convolution to improve the Darknet-53 basic network, and it reduces the amount of calculation and parameters of the network. A multiscale feature pyramid is built, and an attention guidance module is designed to strengthen multiscale fusion, detecting different sizes of targets. The loss function is improved to solve the imbalance of positive and negative sample distribution and the imbalance between simple samples and difficult samples. The Bayesian function is adopted to optimize the classifier and improve the classification efficiency and accuracy, ensuring the accuracy of small target detection. Five groups of comparative experiments are carried out on public COCO and VOC2012 datasets and self-built datasets. The experimental results show that the proposed improved YOLOv3 model can effectively improve the detection accuracy of multiple faces and small targets. Compared with the traditional YOLOv3 model, the mean mAP of the target is improved by more than 1.2%.

scholarly journals Edge Intelligent Perception Method for Power Grid Icing Condition Based on Multi-Scale Feature Fusion Target Detection and Model Quantization

2021 ◽  
Vol 9 ◽  
Author(s):  
Fuqi Ma ◽  
Bo Wang ◽  
Min Li ◽  
Xuzhu Dong ◽  
Yifan Mao ◽  
...  
Keyword(s):  
Transmission Line ◽  
Target Detection ◽  
Power Transmission ◽  
Feature Fusion ◽  
Classical Method ◽  
Power Transmission Line ◽  
Stable Operation ◽  
Detection Accuracy ◽  
Scale Feature ◽  
Multi Scale

Insulator is an important equipment of power transmission line. Insulator icing can seriously affect the stable operation of power transmission line. So insulator icing condition monitoring has great significance of the safety and stability of power system. Therefore, this paper proposes a lightweight intelligent recognition method of insulator icing thickness for front-end ice monitoring device. In this method, the residual network (ResNet) and feature pyramid network (FPN) are fused to construct a multi-scale feature extraction network framework, so that the shallow features and deep features are fused to reduce the information loss and improve the target detection accuracy. Then, the full convolution neural network (FCN) is used to classify and regress the iced insulator, so as to realize the high-precision identification of icing thickness. Finally, the proposed method is compressed by model quantization to reduce the size and parameters of the model for adapting the icing monitoring terminal with limited computing resources, and the performance of the method is verified and compared with other classical method on the edge intelligent chip.

scholarly journals A Research on Landslides Automatic Extraction Model Based on the Improved Mask R-CNN

2021 ◽  
Vol 10 (3) ◽  
pp. 168
Author(s):  
Peng Liu ◽  
Yongming Wei ◽  
Qinjun Wang ◽  
Jingjing Xie ◽  
Yu Chen ◽  
...  
Keyword(s):  
Remote Sensing Data ◽  
Extraction Methods ◽  
New Method ◽  
Detection Accuracy ◽  
Sufficient Information ◽  
Automatic Extraction ◽  
Emergency Rescue ◽  
Feature Pyramid ◽  
High Level ◽  
Extraction Model

Landslides are the most common and destructive secondary geological hazards caused by earthquakes. It is difficult to extract landslides automatically based on remote sensing data, which is import for the scenario of disaster emergency rescue. The literature review showed that the current landslides extraction methods mostly depend on expert interpretation which was low automation and thus was unable to provide sufficient information for earthquake rescue in time. To solve the above problem, an end-to-end improved Mask R-CNN model was proposed. The main innovations of this paper were (1) replacing the feature extraction layer with an effective ResNeXt module to extract the landslides. (2) Increasing the bottom-up channel in the feature pyramid network to make full use of low-level positioning and high-level semantic information. (3) Adding edge losses to the loss function to improve the accuracy of the landslide boundary detection accuracy. At the end of this paper, Jiuzhaigou County, Sichuan Province, was used as the study area to evaluate the new model. Results showed that the new method had a precision of 95.8%, a recall of 93.1%, and an overall accuracy (OA) of 94.7%. Compared with the traditional Mask R-CNN model, they have been significantly improved by 13.9%, 13.4%, and 9.9%, respectively. It was proved that the new method was effective in the landslides automatic extraction.

scholarly journals MTI-YOLO: A Light-Weight and Real-Time Deep Neural Network for Insulator Detection in Complex Aerial Images

Energies ◽  
2021 ◽  
Vol 14 (5) ◽  
pp. 1426
Author(s):  
Chuanyang Liu ◽  
Yiquan Wu ◽  
Jingjing Liu ◽  
Jiaming Han
Keyword(s):  
Feature Detection ◽  
Feature Fusion ◽  
Memory Storage ◽  
Aerial Images ◽  
Detection Accuracy ◽  
Composite Insulator ◽  
Running Time ◽  
Scale Feature ◽  
Multi Scale ◽  
Good Trade

Insulator detection is an essential task for the safety and reliable operation of intelligent grids. Owing to insulator images including various background interferences, most traditional image-processing methods cannot achieve good performance. Some You Only Look Once (YOLO) networks are employed to meet the requirements of actual applications for insulator detection. To achieve a good trade-off among accuracy, running time, and memory storage, this work proposes the modified YOLO-tiny for insulator (MTI-YOLO) network for insulator detection in complex aerial images. First of all, composite insulator images are collected in common scenes and the “CCIN_detection” (Chinese Composite INsulator) dataset is constructed. Secondly, to improve the detection accuracy of different sizes of insulator, multi-scale feature detection headers, a structure of multi-scale feature fusion, and the spatial pyramid pooling (SPP) model are adopted to the MTI-YOLO network. Finally, the proposed MTI-YOLO network and the compared networks are trained and tested on the “CCIN_detection” dataset. The average precision (AP) of our proposed network is 17% and 9% higher than YOLO-tiny and YOLO-v2. Compared with YOLO-tiny and YOLO-v2, the running time of the proposed network is slightly higher. Furthermore, the memory usage of the proposed network is 25.6% and 38.9% lower than YOLO-v2 and YOLO-v3, respectively. Experimental results and analysis validate that the proposed network achieves good performance in both complex backgrounds and bright illumination conditions.

scholarly journals Extended Feature Pyramid Network with Adaptive Scale Training Strategy and Anchors for Object Detection in Aerial Images

2020 ◽  
Vol 12 (5) ◽  
pp. 784 ◽  
Author(s):  
Wei Guo ◽  
Weihong Li ◽  
Weiguo Gong ◽  
Jinkai Cui
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Semantic Information ◽  
Aerial Images ◽  
Training Strategy ◽  
The Public ◽  
Multi Scale ◽  
Shallow Layer ◽  
The Neural Network ◽  
Feature Pyramid

Multi-scale object detection is a basic challenge in computer vision. Although many advanced methods based on convolutional neural networks have succeeded in natural images, the progress in aerial images has been relatively slow mainly due to the considerably huge scale variations of objects and many densely distributed small objects. In this paper, considering that the semantic information of the small objects may be weakened or even disappear in the deeper layers of neural network, we propose a new detection framework called Extended Feature Pyramid Network (EFPN) for strengthening the information extraction ability of the neural network. In the EFPN, we first design the multi-branched dilated bottleneck (MBDB) module in the lateral connections to capture much more semantic information. Then, we further devise an attention pathway for better locating the objects. Finally, an augmented bottom-up pathway is conducted for making shallow layer information easier to spread and further improving performance. Moreover, we present an adaptive scale training strategy to enable the network to better recognize multi-scale objects. Meanwhile, we present a novel clustering method to achieve adaptive anchors and make the neural network better learn data features. Experiments on the public aerial datasets indicate that the presented method obtain state-of-the-art performance.

scholarly journals Pedestrian detection algorithm based on improved muti-scale feature fusion

2021 ◽  
Vol 2078 (1) ◽  
pp. 012008
Author(s):  
Hui Liu ◽  
Keyang Cheng
Keyword(s):  
Clustering Algorithm ◽  
Feature Fusion ◽  
Pedestrian Detection ◽  
Detection Algorithm ◽  
Data Sets ◽  
False Detection ◽  
Scale Feature ◽  
Multi Scale ◽  
Dilated Convolution ◽  
Small Targets

Abstract Aiming at the problem of false detection and missed detection of small targets and occluded targets in the process of pedestrian detection, a pedestrian detection algorithm based on improved multi-scale feature fusion is proposed. First, for the YOLOv4 multi-scale feature fusion module PANet, which does not consider the interaction relationship between scales, PANet is improved to reduce the semantic gap between scales, and the attention mechanism is introduced to learn the importance of different layers to strengthen feature fusion; then, dilated convolution is introduced. Dilated convolution reduces the problem of information loss during the downsampling process; finally, the K-means clustering algorithm is used to redesign the anchor box and modify the loss function to detect a single category. The experimental results show that the improved pedestrian detection algorithm in the INRIA and WiderPerson data sets under different congestion conditions, the AP reaches 96.83% and 59.67%, respectively. Compared with the pedestrian detection results of the YOLOv4 model, the algorithm improves by 2.41% and 1.03%, respectively. The problem of false detection and missed detection of small targets and occlusion has been significantly improved.

scholarly journals Bacterial colonies detecting and counting based on enhanced CNN detection method

2021 ◽  
Vol 233 ◽  
pp. 02012
Author(s):  
Shousheng Liu ◽  
Zhigang Gai ◽  
Xu Chai ◽  
Fengxiang Guo ◽  
Mei Zhang ◽  
...  
Keyword(s):  
Target Detection ◽  
Error Detection ◽  
Detection Rate ◽  
Detection Method ◽  
Difficult Problem ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Detection Model ◽  
Confidence Threshold ◽  
Small Targets

Bacterial colonies detecting and counting is tedious and time-consuming work. Fortunately CNN (convolutional neural network) detection methods are effective for target detection. The bacterial colonies are a kind of small targets, which have been a difficult problem in the field of target detection technology. This paper proposes a small target enhancement detection method based on double CNNs, which can not only improve the detection accuracy, but also maintain the detection speed similar to the general detection model. The detection method uses double CNNs. The first CNN uses SSD_MOBILENET_V1 network with both target positioning and target recognition functions. The candidate targets are screened out with a low confidence threshold, which can ensure no missing detection of small targets. The second CNN obtains candidate target regions according to the first round of detection, intercepts image sub-blocks one by one, uses the MOBILENET_V1 network to filter out targets with a higher confidence threshold, which can ensure good detection of small targets. Through the two-round enhancement detection method has been transplanted to the embedded platform NVIDIA Jetson AGX Xavier, the detection accuracy of small targets is significantly improved, and the target error detection rate and missed detection rate are reduced to less than 1%.

Sign in / Sign up

Export Citation Format

Share Document