Abstract
Object detection in high-resolution remote sensing images has been attracted increasing attention in recent years owing to the successful applications of civil and military. However, there are many critical challenges deciding the performance of object detection in large-scale complex remote sensing image. One of these challenges is how extract and enhance the discriminative features without the top-down feedback mechanism for the existing convolutional neural network (CNN). To cope with this problem, a novel object detection algorithm based on direct feedback control for CNN (DFCCNN) is proposed in this paper. The DFCCNN combines a region proposal network with an object detection network to generate the proposals and to detect the object separately. Initially, a candidate region proposal network (CRPN) is implemented to extract candidate regions within the remote sensing image. Then multi-class objects detection feedback network (MODFN) propose a new top-down feedback mechanism based on the traditional feedforward network to detect the objects. A direct feedback loop (DFL) and a feedback control layer (FCL) are contained in the feedback network. The DFL propagates the posterior information directly from the top layer without depending on the rest of the network and the FCL make full use of top-down information to inhibit object-irrelevant neurons and emphasize object-relevant neurons. Through the addition of direct feedback control mechanism, these object-relevant neurons can be emphasized by taking feedback information of top layer into feature extraction, whereas these object-irrelevant neurons can be inhibited effectively by pruning the neural pathway. The proposed DFCCNN model is able to extract more discriminative low-level features under the guidance of the high-level information. Some experiments on NWPU VHR-10 data set and aircraft data set are induced, and the experimental results show that the proposed method can achieve a higher accuracy of object detection in remote sensing image with various complex background clutter.
Highlights
A large number of available remote sensing images promote the correlation research in understanding remote sensing image content such as scene classification [1]–[4], The associate editor coordinating the review of this manuscript and approving it for publication was Lefei Zhang .image retrieval [5]–[7], airplane detection [8], [9], vehicle detection [10], building detection [11], etc. [12]
There are 650 optical remote sensing images contained within the NWPU very high resolution (VHR)-10 dataset, in which 565 color images were got from Google Earth with the spatial resolution ranging from 0.5 to 2 m, and 85 color images were acquired from Vaihingen data with a spatial resolution of 0.08 m
In this paper, a novel deep learning-based object detection framework direct feedback control for CNN (DFCCNN) is proposed for remote sensing images
Summary
A large number of available remote sensing images promote the correlation research in understanding remote sensing image content such as scene classification [1]–[4], The associate editor coordinating the review of this manuscript and approving it for publication was Lefei Zhang. Faster R-CNN further improves the computation speed by integrating the region proposal and detection procedure into a unified network These CNN-based algorithms have made a remarkable progress in natural image classification and object detection, especially in the extraction and fusion of hidden features. In order to make use of the top-down information accurately, a novel object detection algorithm based on direct feedback control for CNN (DFCCNN) is proposed to extract more effective features in order to enhance the object detection in this paper. Similar to Faster R-CNN, this method consists of two subnetworks: a candidate region proposal network (CRPN) and a multi-class object detection feedback network (MODFN) They share the convolution layer for endto-end training.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
