Patent
Depth significance-based remote sensing image rapid retrieval method
Reads0
Chats0
TLDR
In this paper, a depth significance-based remote sensing image rapid retrieval method is disclosed and belongs to the field of computer vision, where a full convolution neural network is adopted for constructing a multitask significance object detection model which is used for doing significance detection tasks and semantic segmentation tasks at the same time, and depth significance characteristics of the remote sensing images are learnt in network pre-training processes.Abstract:
A depth significance-based remote sensing image rapid retrieval method is disclosed and belongs to the field of computer vision. The method disclosed in the invention specifically relates to technologies such as in-depth learning, significance object detection, image retrieval and the like. According the method, remote sensing images are research objects, and in-depth learning technologies are used for researching a remote sensing image rapid retrieval method. A full convolution neural network is adopted for constructing a multitask significance object detection model which is used for doing significance detection tasks and semantic segmentation tasks at the same time, and depth significance characteristics of the remote sensing images are learnt in network pre-training processes. A depth network structure is improved, a Hash layer fine tuning network is added, and binary system Hash codes of the remote sensing images can be obtained via learning. Significance characteristics and the Hash codes are used comprehensively for similarity measurement. The method disclosed in the invention is of high application value for realizing accurate, highly efficient and feasible retrieval of the remote sensing images.read more
Citations
More filters
Patent
Fine-grained human face image fast retrieval method based on deep learning
Liu Weixin,Ma Lei,Zhang Xueting +2 more
TL;DR: In this paper, a fine-grained human face image image fast retrieval method based on deep learning was proposed, which consisted of the following steps that a deep convolution neural network model was established, and a loss layer used for calculating a loss function was added to each branch layer of the deep convolutions neural network.
Patent
High-precision clothing image retrieval method and system based on visual attention model
TL;DR: In this paper, a high-precision clothing image retrieval method and system based on a visual attention model was proposed, which includes the steps of feature map extraction: for an input image to be retrieved, extracting the feature map composed of floating-point number with the fixed size by using a deep neural network; attention map extraction for the input image and extracting the attention map using a neural full-convolution depth network.
Patent
Agro-ecological multi-source heterogeneous big data collection, processing and analysis architecture
TL;DR: In this paper, an agro-ecological multi-source heterogeneous big data collection, processing and analysis architecture is presented, which relates to the technical field of artificial intelligence and datamining analysis.
Patent
Method for detecting RGB-D (red, green and blue-depth) three-dimensional objects on basis of deep learning
TL;DR: In this article, a method for detecting RGB-D (red, green and blue-depth) three-dimensional objects on the basis of deep learning is proposed. But the method is limited to the detection of 3D objects.
Patent
Remote sensing image ground object classification method based on superpixel coding and convolution neural network
Jiao Licheng,Rong Qu,Li Ge,Zhang Dan,Tang Xu,Chen Puhua,Ma Wenping,Hou Biao,Yang Shuyuan,Shang Ronghua +9 more
TL;DR: In this paper, a remote sensing image ground object classification method based on superpixel coding and convolution neural network, using adaptive super pixel coding and double channel convolutional neural network is presented.
References
More filters
Proceedings ArticleDOI
The Secrets of Salient Object Segmentation
TL;DR: An extensive evaluation of fixation prediction and salient object segmentation algorithms as well as statistics of major datasets identifies serious design flaws of existing salient object benchmarks and proposes a new high quality dataset that offers both fixation and salient objects segmentation ground-truth.
Proceedings Article
Supervised hashing for image retrieval via image representation learning
TL;DR: Extensive empirical evaluations on three benchmark datasets with different kinds of images show that the proposed method has superior performance gains over several state-of-the-art supervised and unsupervised hashing methods.
Patent
Vehicle type recognition method based on rapid R-CNN deep neural network
TL;DR: In this article, a vehicle type recognition method based on a rapid R-CNN deep neural network, which mainly comprises unsupervised deep learning, a multilayer CNN (Convolutional Neural Network), a regional advice network, network sharing and a softmax classifier, is presented.
Patent
Apparatus and methods for activity-based plasticity in a spiking neuron network
Botond Szatmary,Micah Richert +1 more
TL;DR: In this paper, an activity-based plasticity mechanism was used to potentiate connections between units of the same type (red-red) and depressed connections between different types (red and green) during network operation.
Patent
Tongue body self-diagnosis health cloud service system based on deep convolution neural network
TL;DR: In this paper, a self-diagnosis health cloud service system based on a deep convolution neural network is presented, which consists of a convolutional neural network used for deep learning and training recognition, a tongue body segmentation method based on the deep CNN, and a health cloud platform used for conducting selfdiagnosis according to a recognized tongue image type.
Related Papers (5)
Remote sensing image retrieval method based on multi-agent system
Qimin Cheng,Xing Wang,Liu Jun +2 more