A novel deep learning‐based single shot multibox detector model for object detection in optical remote sensing images

Abstract

Remote sensing image object detection is widely used in civil and military fields. The important task is to detect objects such as ships, planes, airports, harbours and so on, and then it can obtain object category and position information. It is of great significance to use remote sensing images to observe the densely arranged and directional targets such as cars and ships parked in parking lots and harbours. The object detection task mainly includes object localization and classification. Remote sensing images contain large number of small objects and dense scenes due to the long shooting distance and wide coverage. Small objects occupy few pixels in the image, and they are easily miss‐detected. In dense scenes, the overlapping part of each object is large, so it is easy to detect objects repeatedly. The traditional small object detection methods deliver low accuracy and take long time. Therefore, object detection is very challenging. We put forward a novel deep learning‐based single shot multibox detector (SSD) model for object detection. First, we propose an improved inception network to optimize SSD to strengthen the small object feature extraction ability (FEA) in the shallow network. Second, the feature pyramid network is modified to enhance the fusion effect. Third, the deep feature fusion module is designed to improve the FEA of the deep network. Finally, the extracted image features are matched with candidate boxes with different aspect ratios to perform object detection and location with different scales. Experiments on DOTA show that the proposed algorithm can adapt to the remote sensing object detection in different backgrounds, and effectively improve the detection effect of remote sensing objects in complex scenes.

G2Grad-CAMRL: An Object Detection and Interpretation Model Based on Gradient-Weighted Class Activation Mapping and Reinforcement Learning in Remote Sensing Images

“…I c is obtained by projecting P c into the RGB space with the value range [0,255]. The final thermodynamic map of Grad-CAM is obtained by superimposing I c with the original image I o through Equation (19).…”

“…Yan et al [18] proposed the method of gradient attribution, which used the gradient of each pixel in the input model to understand the association between the input and the prediction results. In addition, there are also some visualization methods [19,20], such as visualizing the regions with large activation values of convolution kernel and analyzing the information obtained by the model in the image. These interpretable methods generally use human subjective judgment and lack in-depth analysis.…”

Global and local feature fusion via long and short-term memory mechanism for dance emotion recognition in robot

“…LSTM network for FRI reconfiguration m,n } between the input sample y n and the feature sequence y Sinc m . The forgetting gate in the LSTM model determines the retention and discarding of waveform information in the cell state of the LSTM unit at the last moment (Wang et al, 2022), and reads the output h t−1 of the LSTM unit at the last moment and the input y n,t of the LSTM unit at the current moment. The information is then filtered through the activation function sigmoid(x).…”

A Multiagent Cooperative Decision-Making Method for Adaptive Intersection Complexity Based on Hierarchical RL

“…With the development and extension of the Internet applications, Internet of Things (IoT) [5] gets great development; especially with the help of a new generation of computing models represented by fog computing [6], a large number of new models and new businesses have sprung up represented by smart transportation [7][8][9], smart medical care [10][11][12][13][14], smart education [15], smart agriculture [16], and industrial Internet [17][18][19]. 'Smart +' opens the door to us, and our lives have changed.…”