An SAR Ship Object Detection Algorithm Based on Feature Information Efficient Representation Network

Abstract

In the synthetic aperture radar (SAR) ship image, the target size is small and dense, the background is complex and changeable, the ship target is difficult to distinguish from the surrounding background, and there are many ship-like targets in the image. This makes it difficult for deep-learning-based target detection algorithms to obtain effective feature information, resulting in missed and false detection. The effective expression of the feature information of the target to be detected is the key to the target detection algorithm. How to improve the clear expression of image feature information in the network has always been a difficult point. Aiming at the above problems, this paper proposes a new target detection algorithm, the feature information efficient representation network (FIERNet). The algorithm can extract better feature details, enhance network feature fusion and information expression, and improve model detection capabilities. First, the convolution transformer feature extraction (CTFE) module is proposed, and a convolution transformer feature extraction network (CTFENet) is built with this module as a feature extraction block. The network enables the model to obtain more accurate and comprehensive feature information, weakens the interference of invalid information, and improves the overall performance of the network. Second, a new effective feature information fusion (EFIF) module is proposed to enhance the transfer and fusion of the main information of feature maps. Finally, a new frame-decoding formula is proposed to further improve the coincidence between the predicted frame and the target frame and obtain more accurate picture information. Experiments show that the method achieves 94.14% and 92.01% mean precision (mAP) on SSDD and SAR-ship datasets, and it works well on large-scale SAR ship images. In addition, FIERNet greatly reduces the occurrence of missed detection and false detection in SAR ship detection. Compared to other state-of-the-art object detection algorithms, FIERNet outperforms them on various performance metrics on SAR images.

Pomelo Tree Detection Method Based on Attention Mechanism and Cross-Layer Feature Fusion

“…To improve recognition accuracy in complex environments, some researchers incorporated attention mechanisms into neural network models [48][49][50], and some researchers used feature-fusion modules that combine features at different scales to enable the network to extract richer features [51][52][53]. However, they did not consider that shallow and deep feature information in deep networks have complimentary characteristics.…”

Transformers for Remote Sensing: A Systematic Review and Analysis

“…Wetland mapping [45] Urban planning Urban building classification [43,91] UIS classification [23,92] Others Small object detection [58] Ship detection [93] RS image captioning [94] Due to the continuous exploration of transformers by researchers, they have been applied quite successfully in different scenarios of RS, playing different roles. However, we…”

“…Agriculture Crop type mapping [83] Rice yield prediction [34] Downy mildew disease detection [33] Mariculture cage segmentation [84] Environment protection Smoke-like scenes classification [85] Building damage assessment [86] Detection of melt ponds on sea ice [87] Oil spills detection [88] Deforestation monitoring [89] Snowmelt flood susceptibility assessment [90] Tailings ponds detection [82] Mapping Wetland mapping [45] Urban planning Urban building classification [43,91] UIS classification [23,92] Others Small object detection [58] Ship detection [93] RS image captioning [94] Due to the continuous exploration of transformers by researchers, they have been applied quite successfully in different scenarios of RS, playing different roles. However, we found that the current research of transformers in RS is only limited to observation related to the environment, whether it is the natural environment or urban environment.…”

Infrared Target Detection Based on Interval Sampling Weighting and 3D Attention Head in Complex Scenario

“…The detection head body of YOLOv5 includes three detectors, three scales of gridbased preset prior boxes allocated in each prediction feature layer, and the predictor is utilized to slide the processed fusion feature layer [35]. When the predictor slides to a specific grid, its confidence parameters and regression parameters are predicted for each prior box.…”