Improved YOLOv3 with duplex FPN for object detection based on deep learning

YOLOv3 is a deep learning-based real-time object detector and is mainly used in applications such as video surveillance and autonomous vehicles. In this paper, we proposed an improved YOLOv3 (You Only Look Once version 3) applied Duplex FPN, which enhanced large object detection by utilizing low-level feature information. The conventional YOLOv3 improved the small object detection performance by applying FPN (Feature Pyramid Networks) structure to YOLOv2. However, YOLOv3 with an FPN structure specialized in detecting small objects, so it is difficult to detect large objects. Therefore, this paper proposed an improved YOLOv3 applied Duplex FPN, which can utilize low-level location information in high-level feature maps instead of the existing FPN structure of YOLOv3. This improved the detection accuracy of large objects. Also, an extra detection layer was added to the top-level feature map to prevent failure of detection of parts of large objects. Further, dimension clusters of each detection layer were reassigned to learn quickly how to accurately detect objects. The proposed method was compared and analyzed in the PASCAL VOC dataset. The experimental results showed that the bounding box accuracy of large objects improved owing to the Duplex FPN and extra detection layer, and the proposed method succeeded in detecting large objects that the existing YOLOv3 did not.

Download Full-text

An Evaluation of Deep Learning Methods for Small Object Detection

Journal of Electrical and Computer Engineering ◽

10.1155/2020/3189691 ◽

2020 ◽

Vol 2020 ◽

pp. 1-18 ◽

Cited By ~ 2

Author(s):

Nhat-Duy Nguyen ◽

Tien Do ◽

Thanh Duc Ngo ◽

Duy-Dinh Le

Keyword(s):

Deep Learning ◽

Object Detection ◽

State Of The Art ◽

Rapid Development ◽

Empirical Evaluation ◽

Grid Cell ◽

Small Object ◽

Feature Maps ◽

Comparative Results ◽

Small Object Detection

Small object detection is an interesting topic in computer vision. With the rapid development in deep learning, it has drawn attention of several researchers with innovations in approaches to join a race. These innovations proposed comprise region proposals, divided grid cell, multiscale feature maps, and new loss function. As a result, performance of object detection has recently had significant improvements. However, most of the state-of-the-art detectors, both in one-stage and two-stage approaches, have struggled with detecting small objects. In this study, we evaluate current state-of-the-art models based on deep learning in both approaches such as Fast RCNN, Faster RCNN, RetinaNet, and YOLOv3. We provide a profound assessment of the advantages and limitations of models. Specifically, we run models with different backbones on different datasets with multiscale objects to find out what types of objects are suitable for each model along with backbones. Extensive empirical evaluation was conducted on 2 standard datasets, namely, a small object dataset and a filtered dataset from PASCAL VOC 2007. Finally, comparative results and analyses are then presented.

Download Full-text

Small Object Detection in Traffic Scenes Based on Attention Feature Fusion

Sensors ◽

10.3390/s21093031 ◽

2021 ◽

Vol 21 (9) ◽

pp. 3031

Author(s):

Jing Lian ◽

Yuhang Yin ◽

Linhui Li ◽

Zhenghao Wang ◽

Yafu Zhou

Keyword(s):

Object Detection ◽

Feature Fusion ◽

Contextual Information ◽

Detection Accuracy ◽

Small Object ◽

Limited Information ◽

Feature Maps ◽

Multi Scale ◽

Validation Set ◽

Small Object Detection

There are many small objects in traffic scenes, but due to their low resolution and limited information, their detection is still a challenge. Small object detection is very important for the understanding of traffic scene environments. To improve the detection accuracy of small objects in traffic scenes, we propose a small object detection method in traffic scenes based on attention feature fusion. First, a multi-scale channel attention block (MS-CAB) is designed, which uses local and global scales to aggregate the effective information of the feature maps. Based on this block, an attention feature fusion block (AFFB) is proposed, which can better integrate contextual information from different layers. Finally, the AFFB is used to replace the linear fusion module in the object detection network and obtain the final network structure. The experimental results show that, compared to the benchmark model YOLOv5s, this method has achieved a higher mean Average Precison (mAP) under the premise of ensuring real-time performance. It increases the mAP of all objects by 0.9 percentage points on the validation set of the traffic scene dataset BDD100K, and at the same time, increases the mAP of small objects by 3.5%.

Download Full-text

ZoomInNet: A Novel Small Object Detector in Drone Images with Cross-Scale Knowledge Distillation

Remote Sensing ◽

10.3390/rs13061198 ◽

2021 ◽

Vol 13 (6) ◽

pp. 1198

Author(s):

Bi-Yuan Liu ◽

Huai-Xin Chen ◽

Zhou Huang ◽

Xing Liu ◽

Yun-Zhi Yang

Keyword(s):

Object Detection ◽

Feature Representation ◽

Detection Accuracy ◽

Small Object ◽

Feature Maps ◽

Ground Object ◽

Knowledge Distillation ◽

The Cross ◽

The Difference ◽

Small Object Detection

Drone-based object detection has been widely applied in ground object surveillance, urban patrol, and some other fields. However, the dramatic scale changes and complex backgrounds of drone images usually result in weak feature representation of small objects, which makes it challenging to achieve high-precision object detection. Aiming to improve small objects detection, this paper proposes a novel cross-scale knowledge distillation (CSKD) method, which enhances the features of small objects in a manner similar to image enlargement, so it is termed as ZoomInNet. First, based on an efficient feature pyramid network structure, the teacher and student network are trained with images in different scales to introduce the cross-scale feature. Then, the proposed layer adaption (LA) and feature level alignment (FA) mechanisms are applied to align the feature size of the two models. After that, the adaptive key distillation point (AKDP) algorithm is used to get the crucial positions in feature maps that need knowledge distillation. Finally, the position-aware L2 loss is used to measure the difference between feature maps from cross-scale models, realizing the cross-scale information compression in a single model. Experiments on the challenging Visdrone2018 dataset show that the proposed method draws on the advantages of the image pyramid methods, while avoids the large calculation of them and significantly improves the detection accuracy of small objects. Simultaneously, the comparison with mainstream methods proves that our method has the best performance in small object detection.

Download Full-text

FASSD: A Feature Fusion and Spatial Attention-Based Single Shot Detector for Small Object Detection

Electronics ◽

10.3390/electronics9091536 ◽

2020 ◽

Vol 9 (9) ◽

pp. 1536

Author(s):

Deng Jiang ◽

Bei Sun ◽

Shaojing Su ◽

Zhen Zuo ◽

Peng Wu ◽

...

Keyword(s):

Object Detection ◽

Spatial Attention ◽

Feature Fusion ◽

Single Shot ◽

Small Object ◽

Feature Maps ◽

Feature Representations ◽

Small Object Detection ◽

High Level ◽

Detection Speed

Deep learning methods have significantly improved object detection performance, but small object detection remains an extremely difficult and challenging task in computer vision. We propose a feature fusion and spatial attention-based single shot detector (FASSD) for small object detection. We fuse high-level semantic information into shallow layers to generate discriminative feature representations for small objects. To adaptively enhance the expression of small object areas and suppress the feature response of background regions, the spatial attention block learns a self-attention mask to enhance the original feature maps. We also establish a small object dataset (LAKE-BOAT) of a scene with a boat on a lake and tested our algorithm to evaluate its performance. The results show that our FASSD achieves 79.3% mAP (mean average precision) on the PASCAL VOC2007 test with input 300 × 300, which outperforms the original single shot multibox detector (SSD) by 1.6 points, as well as most improved algorithms based on SSD. The corresponding detection speed was 45.3 FPS (frame per second) on the VOC2007 test using a single NVIDIA TITAN RTX GPU. The test results of a simplified FASSD on the LAKE-BOAT dataset indicate that our model achieved an improvement of 3.5% mAP on the baseline network while maintaining a real-time detection speed (64.4 FPS).

Download Full-text

Multi-View Object Detection Based on Deep Learning

Applied Sciences ◽

10.3390/app8091423 ◽

2018 ◽

Vol 8 (9) ◽

pp. 1423 ◽

Cited By ~ 15

Author(s):

Cong Tang ◽

Yongshun Ling ◽

Xing Yang ◽

Wei Jin ◽

Chao Zheng

Keyword(s):

Deep Learning ◽

Object Detection ◽

Regression Models ◽

Detection Methods ◽

Detection Accuracy ◽

Single Shot ◽

Small Object ◽

Object Retrieval ◽

Detection Approach ◽

Small Object Detection

A multi-view object detection approach based on deep learning is proposed in this paper. Classical object detection methods based on regression models are introduced, and the reasons for their weak ability to detect small objects are analyzed. To improve the performance of these methods, a multi-view object detection approach is proposed, and the model structure and working principles of this approach are explained. Additionally, the object retrieval ability and object detection accuracy of both the multi-view methods and the corresponding classical methods are evaluated and compared based on a test on a small object dataset. The experimental results show that in terms of object retrieval capability, Multi-view YOLO (You Only Look Once: Unified, Real-Time Object Detection), Multi-view YOLOv2 (based on an updated version of YOLO), and Multi-view SSD (Single Shot Multibox Detector) achieve AF (average F-measure) scores that are higher than those of their classical counterparts by 0.177, 0.06, and 0.169, respectively. Moreover, in terms of the detection accuracy, when difficult objects are not included, the mAP (mean average precision) scores of the multi-view methods are higher than those of the classical methods by 14.3%, 7.4%, and 13.1%, respectively. Thus, the validity of the approach proposed in this paper has been verified. In addition, compared with state-of-the-art methods based on region proposals, multi-view detection methods are faster while achieving mAPs that are approximately the same in small object detection.

Download Full-text

Small Object Detection of Table Tennis Based on Deep Learning Network

2020 International Conference on Computer Science and Management Technology (ICCSMT) ◽

10.1109/iccsmt51754.2020.00036 ◽

2020 ◽

Author(s):

Weijian Li ◽

Xiaofeng Tan ◽

Zhijie Wang

Keyword(s):

Deep Learning ◽

Object Detection ◽

Small Object ◽

Table Tennis ◽

Learning Network ◽

Deep Learning Network ◽

Small Object Detection

Download Full-text

Small Targets Detection for Transmission Tower Based on SRGAN and Faster RCNN

Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering) ◽

10.2174/2352096514666211026143543 ◽

2021 ◽

Vol 14 ◽

Author(s):

Runze Liu ◽

Guangwei Yan ◽

Hui He ◽

Yubin An ◽

Ting Wang ◽

...

Keyword(s):

Object Detection ◽

Super Resolution ◽

Generative Adversarial Networks ◽

Stable Operation ◽

Detection Accuracy ◽

Small Object ◽

Detection Model ◽

Tower Equipment ◽

Small Object Detection ◽

Small Targets

Background: Power line inspection is essential to ensure the safe and stable operation of the power system. Object detection for tower equipment can significantly improve inspection efficiency. However, due to the low resolution of small targets and limited features, the detection accuracy of small targets is not easy to improve. Objective: This study aimed to improve the tiny targets’ resolution while making the small target's texture and detailed features more prominent to be perceived by the detection model. Methods: In this paper, we propose an algorithm that employs generative adversarial networks to improve small objects' detection accuracy. First, the original image is converted into a super-resolution one by a super-resolution reconstruction network (SRGAN). Then the object detection framework Faster RCNN is utilized to detect objects on the super-resolution images. Result: The experimental results on two small object recognition datasets show that the model proposed in this paper has good robustness. It can especially detect the targets missed by Faster RCNN, which indicates that SRGAN can effectively enhance the detailed information of small targets by improving the resolution. Conclusion: We found that higher resolution data is conducive to obtaining more detailed information of small targets, which can help the detection algorithm achieve higher accuracy. The small object detection model based on the generative adversarial network proposed in this paper is feasible and more efficient. Compared with Faster RCNN, this model has better performance on small object detection.

Download Full-text

Building Extraction in Very High Resolution Imagery by Dense-Attention Networks

Remote Sensing ◽

10.3390/rs10111768 ◽

2018 ◽

Vol 10 (11) ◽

pp. 1768 ◽

Cited By ~ 24

Author(s):

Hui Yang ◽

Penghai Wu ◽

Xuedong Yao ◽

Yanlan Wu ◽

Biao Wang ◽

...

Keyword(s):

Deep Learning ◽

High Resolution ◽

Building Extraction ◽

Learning Networks ◽

Feature Maps ◽

Low Level ◽

High Resolution Imagery ◽

Very High Resolution Imagery ◽

High Level ◽

Very High

Building extraction from very high resolution (VHR) imagery plays an important role in urban planning, disaster management, navigation, updating geographic databases, and several other geospatial applications. Compared with the traditional building extraction approaches, deep learning networks have recently shown outstanding performance in this task by using both high-level and low-level feature maps. However, it is difficult to utilize different level features rationally with the present deep learning networks. To tackle this problem, a novel network based on DenseNets and the attention mechanism was proposed, called the dense-attention network (DAN). The DAN contains an encoder part and a decoder part which are separately composed of lightweight DenseNets and a spatial attention fusion module. The proposed encoder–decoder architecture can strengthen feature propagation and effectively bring higher-level feature information to suppress the low-level feature and noises. Experimental results based on public international society for photogrammetry and remote sensing (ISPRS) datasets with only red–green–blue (RGB) images demonstrated that the proposed DAN achieved a higher score (96.16% overall accuracy (OA), 92.56% F1 score, 90.56% mean intersection over union (MIOU), less training and response time and higher-quality value) when compared with other deep learning methods.

Download Full-text