Small Object Detection with Multiscale Features

The existing object detection algorithm based on the deep convolution neural network needs to carry out multilevel convolution and pooling operations to the entire image in order to extract a deep semantic features of the image. The detection models can get better results for big object. However, those models fail to detect small objects that have low resolution and are greatly influenced by noise because the features after repeated convolution operations of existing models do not fully represent the essential characteristics of the small objects. In this paper, we can achieve good detection accuracy by extracting the features at different convolution levels of the object and using the multiscale features to detect small objects. For our detection model, we extract the features of the image from their third, fourth, and 5th convolutions, respectively, and then these three scales features are concatenated into a one-dimensional vector. The vector is used to classify objects by classifiers and locate position information of objects by regression of bounding box. Through testing, the detection accuracy of our model for small objects is 11% higher than the state-of-the-art models. In addition, we also used the model to detect aircraft in remote sensing images and achieved good results.

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

Infrared Dim-small Object Detection Algorithm Based on Saliency Map Combined with Target Motion Feature

2020 IEEE International Conference on Progress in Informatics and Computing (PIC) ◽

10.1109/pic50277.2020.9350820 ◽

2020 ◽

Author(s):

WenWen Zhang ◽

ZhiChao Lian

Keyword(s):

Object Detection ◽

Detection Algorithm ◽

Saliency Map ◽

Target Motion ◽

Small Object ◽

Motion Feature ◽

Small Object Detection

Download Full-text

An Improved Object Detection Method using Feature Map Refinement and Anchor Optimization

International Journal of Circuits, Systems and Signal Processing ◽

10.46300/9106.2021.15.60 ◽

2021 ◽

Vol 15 ◽

pp. 541-549

Author(s):

Yuxia Wang ◽

Wenzhu Yang ◽

Tongtong Yuan ◽

Qian Li

Keyword(s):

Object Detection ◽

Detection Method ◽

Search Space ◽

Detection Algorithm ◽

Detection Accuracy ◽

Semantic Features ◽

Feature Map ◽

Input Size ◽

Fusion Operation ◽

Different Levels

Lower detection accuracy and insufficient detection ability for small objects are the main problems of the region-free object detection algorithm. Aiming at solving the abovementioned problems, an improved object detection method using feature map refinement and anchor optimization is proposed. Firstly, the reverse fusion operation is performed on each of the object detection layer, which can provide the lower layers with more semantic information by the fusion of detection features at different levels. Secondly, the self-attention module is used to refine each detection feature map, calibrates the features between channels, and enhances the expression ability of local features. In addition, the anchor optimization model is introduced on each feature layer associated with anchors, and the anchors with higher probability of containing an object and more closely match the location and size of the object are obtained. In this model, semantic features are used to confirm and remove negative anchors to reduce search space of the objects, and preliminary adjustments are made to the locations and sizes of anchors. Comprehensive experimental results on PASCAL VOC detection dataset demonstrate the effectiveness of the proposed method. In particular, with VGG-16 and lower dimension 300×300 input size, the proposed method achieves a mAP of 79.1% on VOC 2007 test set with an inference speed of 24.7 milliseconds per image.

Download Full-text

Fast Small Object Detection Algorithm Based on Feature Enhancement and Reconstruction

10.1109/wcsp52459.2021.9613660 ◽

2021 ◽

Author(s):

Zhiyong Huo ◽

Tianwen Yan ◽

Weiye Cao

Keyword(s):

Object Detection ◽

Detection Algorithm ◽

Small Object ◽

Feature Enhancement ◽

Small Object Detection

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

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

International Journal of Electrical Engineering Education ◽

10.1177/0020720920983524 ◽

2021 ◽

pp. 002072092098352

Author(s):

Seokyong Shin ◽

Hyunho Han ◽

Sang Hun Lee

Keyword(s):

Deep Learning ◽

Object Detection ◽

Autonomous Vehicles ◽

Detection Accuracy ◽

Small Object ◽

Feature Maps ◽

Low Level ◽

Small Object Detection ◽

High Level ◽

Networks Structure

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 Improved Swin Transformer-Based Model for Remote Sensing Object Detection and Instance Segmentation

Remote Sensing ◽

10.3390/rs13234779 ◽

2021 ◽

Vol 13 (23) ◽

pp. 4779

Author(s):

Xiangkai Xu ◽

Zhejun Feng ◽

Changqing Cao ◽

Mengyuan Li ◽

Jin Wu ◽

...

Keyword(s):

Remote Sensing ◽

Object Detection ◽

Small Scale ◽

Detection Accuracy ◽

Small Object ◽

Research Fields ◽

Local Perception ◽

Segmentation Accuracy ◽

Small Object Detection ◽

Instance Segmentation

Remote sensing image object detection and instance segmentation are widely valued research fields. A convolutional neural network (CNN) has shown defects in the object detection of remote sensing images. In recent years, the number of studies on transformer-based models increased, and these studies achieved good results. However, transformers still suffer from poor small object detection and unsatisfactory edge detail segmentation. In order to solve these problems, we improved the Swin transformer based on the advantages of transformers and CNNs, and designed a local perception Swin transformer (LPSW) backbone to enhance the local perception of the network and to improve the detection accuracy of small-scale objects. We also designed a spatial attention interleaved execution cascade (SAIEC) network framework, which helped to strengthen the segmentation accuracy of the network. Due to the lack of remote sensing mask datasets, the MRS-1800 remote sensing mask dataset was created. Finally, we combined the proposed backbone with the new network framework and conducted experiments on this MRS-1800 dataset. Compared with the Swin transformer, the proposed model improved the mask AP by 1.7%, mask APS by 3.6%, AP by 1.1% and APS by 4.6%, demonstrating its effectiveness and feasibility.

Download Full-text

CXR-RefineDet: Single-Shot Refinement Neural Network for Chest X-Ray Radiograph Based on Multiple Lesions Detection

Journal of Healthcare Engineering ◽

10.1155/2022/4182191 ◽

2022 ◽

Vol 2022 ◽

pp. 1-11

Author(s):

Cong Lin ◽

Yongbin Zheng ◽

Xiuchun Xiao ◽

Jialun Lin

Keyword(s):

Neural Network ◽

Object Detection ◽

Disease Diagnosis ◽

Detection Algorithm ◽

Detection Accuracy ◽

Single Shot ◽

Detection Model ◽

Network Output ◽

Artificial Intelligence Technology ◽

Chest X Ray

The workload of radiologists has dramatically increased in the context of the COVID-19 pandemic, causing misdiagnosis and missed diagnosis of diseases. The use of artificial intelligence technology can assist doctors in locating and identifying lesions in medical images. In order to improve the accuracy of disease diagnosis in medical imaging, we propose a lung disease detection neural network that is superior to the current mainstream object detection model in this paper. By combining the advantages of RepVGG block and Resblock in information fusion and information extraction, we design a backbone RRNet with few parameters and strong feature extraction capabilities. After that, we propose a structure called Information Reuse, which can solve the problem of low utilization of the original network output features by connecting the normalized features back to the network. Combining the network of RRNet and the improved RefineDet, we propose the overall network which was called CXR-RefineDet. Through a large number of experiments on the largest public lung chest radiograph detection dataset VinDr-CXR, it is found that the detection accuracy and inference speed of CXR-RefineDet have reached 0.1686 mAP and 6.8 fps, respectively, which is better than the two-stage object detection algorithm using a strong backbone like ResNet-50 and ResNet-101. In addition, the fast reasoning speed of CXR-RefineDet also provides the possibility for the actual implementation of the computer-aided diagnosis system.

Download Full-text