Adaptive Weighting Feature Fusion Approach Based on Generative Adversarial Network for Hyperspectral Image Classification

An Intelligent Online Drunk Driving Detection System Based on Multi-Sensor Fusion Technology

Since drunk driving poses a significant threat to road traffic safety, there is an increasing demand for the performance and dependability of online drunk driving detection devices for automobiles. However, the majority of current detection devices only contain a single sensor, resulting in a low degree of detection accuracy, erroneous judgments, and car locking. In order to solve the problem, this study firstly designed a sensor array based on the gas diffusion model and the characteristics of a car steering wheel. Secondly, the data fusion algorithm is proposed according to the data characteristics of the sensor array on the steering wheel. The support matrix is used to improve the data consistency of the single sensor data, and then the adaptive weighted fusion algorithm is used for multiple sensors. Finally, in order to verify the reliability of the system, an online intelligent detection device for drunk driving based on multi-sensor fusion was developed, and three people using different combinations of drunk driving simulation experiments were conducted. According to the test results, a drunk person in the passenger seat will not cause the system to make a drunk driving determination. When more than 50 mL of alcohol is consumed and the driver is seated in the driver's seat, the online intelligent detection of drunk driving can accurately identify drunk driving, and the car will lock itself as soon as a real-time online voice prompt is heard. This study enhances and complements theories relating to data fusion for online automobile drunk driving detection, allowing for the online identification of drivers who have been drinking and the locking of their vehicles to prevent drunk driving. It provides technical support for enhancing the accuracy of online systems that detect drunk driving in automobiles.

Hyperspectral Image Classification: Potentials, Challenges, and Future Directions

Recent imaging science and technology discoveries have considered hyperspectral imagery and remote sensing. The current intelligent technologies, such as support vector machines, sparse representations, active learning, extreme learning machines, transfer learning, and deep learning, are typically based on the learning of the machines. These techniques enrich the processing of such three-dimensional, multiple bands, and high-resolution images with their precision and fidelity. This article presents an extensive survey depicting machine-dependent technologies' contributions and deep learning on landcover classification based on hyperspectral images. The objective of this study is three-fold. First, after reading a large pool of Web of Science (WoS), Scopus, SCI, and SCIE-indexed and SCIE-related articles, we provide a novel approach for review work that is entirely systematic and aids in the inspiration of finding research gaps and developing embedded questions. Second, we emphasize contemporary advances in machine learning (ML) methods for identifying hyperspectral images, with a brief, organized overview and a thorough assessment of the literature involved. Finally, we draw the conclusions to assist researchers in expanding their understanding of the relationship between machine learning and hyperspectral images for future research.

Unsupervised Multi-Level Feature Extraction for Improvement of Hyperspectral Classification

Deep learning models have strong abilities in learning features and they have been successfully applied in hyperspectral images (HSIs). However, the training of most deep learning models requires labeled samples and the collection of labeled samples are labor-consuming in HSI. In addition, single-level features from a single layer are usually considered, which may result in the loss of some important information. Using multiple networks to obtain multi-level features is a solution, but at the cost of longer training time and computational complexity. To solve these problems, a novel unsupervised multi-level feature extraction framework that is based on a three dimensional convolutional autoencoder (3D-CAE) is proposed in this paper. The designed 3D-CAE is stacked by fully 3D convolutional layers and 3D deconvolutional layers, which allows for the spectral-spatial information of targets to be mined simultaneously. Besides, the 3D-CAE can be trained in an unsupervised way without involving labeled samples. Moreover, the multi-level features are directly obtained from the encoded layers with different scales and resolutions, which is more efficient than using multiple networks to get them. The effectiveness of the proposed multi-level features is verified on two hyperspectral data sets. The results demonstrate that the proposed method has great promise in unsupervised feature learning and can help us to further improve the hyperspectral classification when compared with single-level features.

Robust Classification Technique for Hyperspectral Images Based on 3D-Discrete Wavelet Transform

Hyperspectral image classification is an emerging and interesting research area that has attracted several researchers to contribute to this field. Hyperspectral images have multiple narrow bands for a single image that enable the development of algorithms to extract diverse features. Three-dimensional discrete wavelet transform (3D-DWT) has the advantage of extracting the spatial and spectral information simultaneously. Decomposing an image into a set of spatial–spectral components is an important characteristic of 3D-DWT. It has motivated us to perform the proposed research work. The novelty of this work is to bring out the features of 3D-DWT applicable to hyperspectral images classification using Haar, Fejér-Korovkin and Coiflet filters. Three-dimensional-DWT is implemented with the help of three stages of 1D-DWT. The first two stages of 3D-DWT are extracting spatial resolution, and the third stage is extracting the spectral content. In this work, the 3D-DWT features are extracted and fed to the following classifiers (i) random forest (ii) K-nearest neighbor (KNN) and (iii) support vector machine (SVM). Exploiting both spectral and spatial features help the classifiers to provide a better classification accuracy. A comparison of results was performed with the same classifiers without DWT features. The experiments were performed using Salinas Scene and Indian Pines hyperspectral datasets. From the experiments, it has been observed that the SVM with 3D-DWT features performs better in terms of the performance metrics such as overall accuracy, average accuracy and kappa coefficient. It has shown significant improvement compared to the state of art techniques. The overall accuracy of 3D-DWT+SVM is 88.3%, which is 14.5% larger than that of traditional SVM (77.1%) for the Indian Pines dataset. The classification map of 3D-DWT + SVM is more closely related to the ground truth map.