The aim of this research is to highlight the advantages of Climate-Smart Agriculture and the progress accomplished by implementing information technology to make agriculture intelligent. The research article also incl...
详细信息
Aerospace images with a spatial resolution of less than 1 m are actively used by regional services to obtain and update information about various environmental objects. Considerable efforts are being devoted to the de...
详细信息
Recently, with the increasing number of large-scale remotesensingimages, the demand for large-scale remotesensingimage object classification is growing and attracting the interest of many researchers. Hashing, bec...
详细信息
ISBN:
(纸本)9781728188089;9781728188096
Recently, with the increasing number of large-scale remotesensingimages, the demand for large-scale remotesensingimage object classification is growing and attracting the interest of many researchers. Hashing, because of its low memory requirements and high time efficiency, has widely solve the problem of large-scale remotesensingimage. Supervised hashing methods mainly leverage the label information of remotesensingimage to learn hash function, however, the similarity of the original feature space cannot be well preserved, which can not meet the accurate requirements for object classification of remotesensingimage. To solve the mentioned problem, we propose a novel method named Optimized Projection Supervised Discrete Hashing(OPSDH), which jointly learns a discrete binary codes generation and optimized projection constraint model. It uses an effective optimized projection method to further constraint the supervised hash learning and generated hash codes preserve the similarity based on the data label while retaining the similarity of the original feature space. The experimental results show that OPSDH reaches improved performance compared with the existing hash learning methods and demonstrate that the proposed method is more efficient for operational applications.
In Data Science, Clustering is one of the most popular techniques. It has wide potential application in data analysis, market research, patternrecognition, imageprocessing, etc. Spectral Clustering is a clustering a...
详细信息
ISBN:
(纸本)9781728176123
In Data Science, Clustering is one of the most popular techniques. It has wide potential application in data analysis, market research, patternrecognition, imageprocessing, etc. Spectral Clustering is a clustering algorithm shows improved performance than the conventional clustering algorithms. To handle Social media multimodal data in Event Clustering and for better understanding of the context of the post, Spectral Clustering of Events in Flood images Based on Multimodal Analysis (SCEFIMA) approach is proposed. This approach makes use of Post's image and textual content (Multimodal data) in Clustering the events. Also considering Spatial and Temporal Information in understanding the post. The existing approaches lacks on multimodal analysis in social media data. Use of Multimodal data gives the better understanding of the context of the post in event clustering. In addition to this, Using Multimodal data in Event Clustering significantly boost performance than the existing methods. Detecting and Clustering events from multimodal data in social networks helpful in monitoring events by public organizations and authorities. Also helpful in early planning for preventive measures.
In the last few years, Earth Observation sensors received a large development, offering, therefore, various types of data with different temporal, spatial, spectral, and radiometric resolutions. However, due to physic...
详细信息
We propose an embarrassingly simple but very effective scheme for high-quality dense stereo reconstruction: (i) generate an approximate reconstruction with your favourite stereo matcher;(ii) rewarp the input images wi...
详细信息
ISBN:
(纸本)9781728193601
We propose an embarrassingly simple but very effective scheme for high-quality dense stereo reconstruction: (i) generate an approximate reconstruction with your favourite stereo matcher;(ii) rewarp the input images with that approximate model;(iii) with the initial reconstruction and the warped images as input, train a deep network to enhance the reconstruction by regressing a residual correction;and (iv) if desired, iterate the refinement with the new, improved reconstruction. The strategy to only learn the residual greatly simplifies the learning problem. A standard Unet without bells and whistles is enough to reconstruct even small surface details, like dormers and roof substructures in satellite images. We also investigate residual reconstruction with less information and find that even a single image is enough to greatly improve an approximate reconstruction. Our full model reduces the mean absolute error of state-of-the-art stereo reconstruction systems by >50%, both in our target domain of satellite stereo and on stereo pairs from the ETH3D benchmark.
The convolutional neural networks have achieved very good results in the field of remotesensingimage classification and recognition. However, the cost of huge computational complexity with the significant accuracy i...
详细信息
ISBN:
(纸本)9789811365041;9789811365034
The convolutional neural networks have achieved very good results in the field of remotesensingimage classification and recognition. However, the cost of huge computational complexity with the significant accuracy improvement of CNNs makes a huge challenge to hardware implementation. A promising solution is FPGA due to it supports parallel computing with low power consumption. In this paper, LeNet-5-based remotesensingimage classification method is implemented on FPGA. The test images with a size of 126 x 126 are transformed to the system from PC by serial port. The classification accuracy is 98.18% tested on the designed system, which is the same as that on PC. In the term of efficiency, the designed system runs 2.29 ms per image, which satisfies the real-time requirements.
Identifying the origin of a sample image in biometric systems can be beneficial for data authentication in case of attacks against the system and initiating sensor-specific processing pipelines in sensor-heterogeneous...
详细信息
ISBN:
(纸本)9783030869601;9783030869595
Identifying the origin of a sample image in biometric systems can be beneficial for data authentication in case of attacks against the system and initiating sensor-specific processing pipelines in sensor-heterogeneous environments. Motivated by shortcomings of the photo response non-uniformity (PRNU) based method in the biometric context, we employ eight texture classification approaches, including frequency-, spatial-, and wavelet-based methods to detect finger vein samples images' origin. Besides, We use eight publicly available finger vein datasets and applying all eight novel classical texture descriptors and SVM classification in the suggested pipeline. A novel wavelet-based approach termed WMV demonstrated an excellent result for raw finger vein samples and the more challenging region of interest data among mentioned employed methods to identify sensor model. The observed results establish texture descriptors as effective competitors to PRNU in finger vein sensor model identification.
In recent years, deep learning methods bring incredible progress to the field of object detection. However, in the field of remotesensingimageprocessing, existing methods neglect the relationship between imaging co...
详细信息
In recent years, deep learning methods bring incredible progress to the field of object detection. However, in the field of remotesensingimageprocessing, existing methods neglect the relationship between imaging configuration and detection performance, and do not take into account the importance of detection performance feedback for improving image quality. Therefore, detection performance is limited by the passive nature of the conventional object detection framework. In order to solve the above limitations, this paper takes adaptive brightness adjustment and scale adjustment as examples, and proposes an active object detection method based on deep reinforcement learning. The goal of adaptive image attribute learning is to maximize the detection performance. With the help of active object detection and image attribute adjustment strategies, low-quality images can be converted into high-quality images, and the overall performance is improved without retraining the detector.
We deal with the problem of generating textual captions from optical remotesensing (RS) images using the notion of deep reinforcement learning. Due to the high inter-class similarity in reference sentences describing...
详细信息
ISBN:
(纸本)9781728188089;9781728188096
We deal with the problem of generating textual captions from optical remotesensing (RS) images using the notion of deep reinforcement learning. Due to the high inter-class similarity in reference sentences describing remotesensing data, jointly encoding the sentences and images encourages prediction of captions that are semantically more precise than the ground truth in many cases. To this end, we introduce an Actor Dual-Critic training strategy where a second critic model is deployed in the form of an encoder-decoder RNN to encode the latent information corresponding to the original and generated captions. While all actor-critic methods use an actor to predict sentences for an image and a critic to provide rewards, our proposed encoder-decoder RNN guarantees high-level comprehension of images by sentence-to-image translation. We observe that the proposed model generates sentences on the test data highly similar to the ground truth and is successful in generating even better captions in many critical cases. Extensive experiments on the benchmark remotesensingimage Captioning Dataset (RSICD) and the UCM-captions dataset confirm the superiority of the proposed approach in comparison to the previous state-of-the-art where we obtain a gain of sharp increments in both the ROUGE-L and CIDEr measures.
暂无评论