With the continuous development of automotive electronics, automotive sensing technology has also appeared and has been more and more widely used. As an important part of the automotive electronic control system, automotive sensors not only need to collect information, but also transmit information. The automobile sensor first needs to convert the automobile operating condition information into electrical signals and then transmit it to the central control unit, in order to make the engine reach the best working condition. In addition, automotive sensors can also perform accurate and real-time measurement and control for information such as pressure, temperature, speed, photoelectricity and flow rate, which greatly improves the effectiveness of information processing. As a factor that can affect the safe operation of a car, the quality of the car sensor plays a direct role. Therefore, in order to ensure the safe operation of automobiles, strict requirements on the accuracy, stability, responsiveness, shock resistance and service life of automobile sensors are required. The development of modern cars is moving towards a safer and more comfortable perspective and the key to achieving this goal lies in the development of sensors. At present, the development of sensors mainly depends on the development of new sensors and the integration, intelligence and multifunction of sensors. Realize the improvement of the sensor’s working accuracy and response speed and the ability to adapt to different environments. Therefore, studying the application of sensors in the current automotive field is of great significance to the future development of the automotive field and the sensor field.

Recently, using spatial–spectral information for hyperspectral anomaly detection (AD) has received extensive attention. However, the test point and its neighborhood points are usually treated equally without highlighting the test point, which is unreasonable. In this paper, improved central attention network-based tensor RX (ICAN-TRX) is designed to extract hyperspectral anomaly targets. The ICAN-TRX algorithm consists of two parts, ICAN and TRX. In ICAN, a test tensor block as a value tensor is first reconstructed by DBN to make the anomaly points more prominent. Then, in the reconstructed tensor block, the central tensor is used as a convolution kernel to perform convolution operation with its tensor block. The result tensor as a key tensor is transformed into a weight matrix. Finally, after the correlation operation between the value tensor and the weight matrix, the new test point is obtained. In ICAN, the spectral information of a test point is emphasized, and the spatial relationships between the test point and its neighborhood points reflect their similarities. TRX is used in the new HSI after ICAN, which allows more abundant spatial information to be used for AD. Five real hyperspectral datasets are selected to estimate the performance of the proposed ICAN-TRX algorithm. The detection results demonstrate that ICAN-TRX achieves superior performance compared with seven other AD algorithms.