YOLOV4_CSPBi: Enhanced Land Target Detection Model

The identification of small land targets in remote sensing imagery has emerged as a significant research objective. Despite significant advancements in object detection strategies based on deep learning for visible remote sensing images, the performance of detecting a small and densely distributed number of small targets remains suboptimal. To address this issue, this study introduces an improved model named YOLOV4_CPSBi, based on the YOLOV4 architecture, specifically designed to enhance the detection capability of small land targets in remote sensing imagery. The proposed model enhances the traditional CSPNet by redefining its channel partitioning and integrating this enhanced structure into the neck part of the YOLO network model. Additionally, the conventional pyramid fusion structure used in the traditional BiFPN is removed. By integrating a weight-based bidirectional multi-scale mechanism for feature fusion, the model is capable of effectively reasoning about objects of various sizes, with a particular focus on detecting small land targets, without introducing a significant increase in computational costs. Using the DOTA dataset as research data, this study quantifies the object detection performance of the proposed model. Compared with various baseline models, for the detection of small targets, its AP performance has been improved by nearly 8% compared with YOLOV4. By combining these modifications, the proposed model demonstrates promising results in identifying small land targets in visible remote sensing images.

[1]  Guicai Li,et al.  Establishing a Reliable Assessment of the Green View Index Based on Image Classification Techniques, Estimation, and a Hypothesis Testing Route , 2023, Land.

[2]  M. Crespi,et al.  Land Consumption Classification Using Sentinel 1 Data: A Systematic Review , 2023, Land.

[3]  Jie Zhan,et al.  Comparison of two deep learning methods for ship target recognition with optical remotely sensed data , 2020, Neural Computing and Applications.

[4]  Ting Wang,et al.  Research on Airplane and Ship Detection of Aerial Remote Sensing Images Based on Convolutional Neural Network , 2020, Sensors.

[5]  Kun Fu,et al.  FMSSD: Feature-Merged Single-Shot Detection for Multiscale Objects in Large-Scale Remote Sensing Imagery , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Jing Zhang,et al.  Object Detection Based on Global-Local Saliency Constraint in Aerial Images , 2020, Remote. Sens..

[7]  Jiayue Yang,et al.  GridMask Based Data Augmentation For Bengali Handwritten Grapheme Classification , 2020 .

[8]  Guisong Xia,et al.  Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Junwei Han,et al.  Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[10]  Qiang Wang,et al.  Multi-Attention Object Detection Model in Remote Sensing Images Based on Multi-Scale , 2019, IEEE Access.

[11]  Dazhuan Xu,et al.  Sig-NMS-Based Faster R-CNN Combining Transfer Learning for Small Target Detection in VHR Optical Remote Sensing Imagery , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Jue Wang,et al.  Detection of Multiclass Objects in Optical Remote Sensing Images , 2019, IEEE Geoscience and Remote Sensing Letters.

[13]  Jin Wang,et al.  A full convolutional network based on DenseNet for remote sensing scene classification. , 2019, Mathematical biosciences and engineering : MBE.

[14]  Zhenbao Liu,et al.  Object Detection in Aerial Images Using Feature Fusion Deep Networks , 2019, IEEE Access.

[15]  Qingmin Liao,et al.  A Study on Radar Target Detection Based on Deep Neural Networks , 2019, IEEE Sensors Letters.

[16]  Amin Sedaghat,et al.  Geospatial Target Detection from High-Resolution Remote-Sensing Images Based on PIIFD Descriptor and Salient Regions , 2019, Journal of the Indian Society of Remote Sensing.

[17]  Uwe Soergel,et al.  Detection of Vehicles in Multisensor Data via Multibranch Convolutional Neural Networks , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[18]  Shuai Li,et al.  Rapid Airplane Detection in Remote Sensing Images Based on Multilayer Feature Fusion in Fully Convolutional Neural Networks , 2018, Sensors.

[19]  Menglong Yan,et al.  Position Detection and Direction Prediction for Arbitrary-Oriented Ships via Multitask Rotation Region Convolutional Neural Network , 2018, IEEE Access.

[20]  Menglong Yan,et al.  Automatic Ship Detection in Remote Sensing Images from Google Earth of Complex Scenes Based on Multiscale Rotation Dense Feature Pyramid Networks , 2018, Remote. Sens..

[21]  Freek D. van der Meer,et al.  Remote-sensing image analysis and geostatistics , 2012 .