This paper presents an efficient mutual interference suppression method using wavelet denoising in automotive radar systems. When a radar signal transmitted from another radar-equipped vehicle flows into our radar system, it acts as an interference signal and degrades the target detection performance. With wavelet denoising, the interference signal can be extracted from the time-domain low-pass filter output. Then, the effect of the interference can be mitigated by subtracting the interference signal from the original low-pass filter output. As a result, the beat frequency containing the target information can be estimated accurately. Simulation results show that the proposed method can enhance the estimation accuracy of the target's distance, velocity, and angle. In addition, the performance of the proposed method is verified through actual experiments using heterogeneous radars. In the measurement results, even though the exact specifications of the radar signal transmitted from the other vehicle are not identified, the interference is effectively suppressed. Unlike other existing methods, the proposed method using wavelet denoising does not need to generate a specific radar waveform and it can mitigate interference only by signal processing without changing the existing hardware.

In this study, a human–vehicle classification using a feature‐based support vector machine (SVM) in a 77‐GHz automotive frequency modulated continuous wave (FMCW) radar system is proposed. As a classification criterion, the authors use a newly defined parameter called root radar cross section which reflects the reflection characteristics of targets. Based on this parameter, three distinctive signal features are extracted from frequency‐domain received FMCW radar signals, and they become classification standards used for the SVM. Finally, through measurement results on the test field, the classification performance of the authors’ proposed method is verified, and the average classification accuracy from a four‐fold cross data validation is found to be higher than 90%. In addition, the authors’ proposed classification method is applied to distinguish a pedestrian, a vehicle, and a cyclist in a more practical situation, and it also shows good classification performance.

This paper proposes a method to simultaneously detect and classify objects by using a deep learning model, specifically you only look once (YOLO), with pre-processed automotive radar signals. In conventional methods, the detection and classification in automotive radar systems are conducted in two successive stages; however, in the proposed method, the two stages are combined into one. To verify the effectiveness of the proposed method, we applied it to the actual radar data measured using our automotive radar sensor. According to the results, our proposed method can simultaneously detect targets and classify them with over 90% accuracy. In addition, it shows better performance in terms of detection and classification, compared with conventional methods such as density-based spatial clustering of applications with noise or the support vector machine. Moreover, the proposed method especially exhibits better performance when detecting and classifying a vehicle with a long body.

Nowadays, various sensors are being widely used in indoor environments to improve quality of life. In particular, sensors can be installed inside a car to detect dangerous situations, such as a child or a pet being left alone in a car. In this paper, we present an effective method for monitoring people inside a vehicle by using impulse radio ultra-wideband radar. First, we identify that the waveform of the received signal varies with the arrangement of people inside the vehicle. Then, we extract features that represent the statistical characteristics of the received signal and use them as classification criteria. To determine the importance of each feature and reduce the number of features, we use a neighborhood component analysis algorithm. Next, we use ensemble learning with a decision tree as a base classifier to classify the various arrangement of people inside the car. The classification results demonstrate that our proposed method successfully estimates the position and number of people sitting inside a vehicle with an accuracy higher than 90%. Moreover, to utilize the proposed method in real time, we derive an appropriate number of features and structure for the classifier, so as to achieve high classification accuracy while keeping the computational complexity low.

This paper proposes an efficient road structure recognition method using statistical characteristics of received signals in automotive frequency-modulated continuous wave radar systems. Generally, roads consist of various structures, some of which, such as tunnels and soundproof walls made of iron, generate undesired echoes, called clutter. When the clutter flows into the radar system, the target detection performance cannot be guaranteed completely. This causes great danger to the driver using the radar function such as adaptive cruise control. Thus, an efficient method to recognize the structures that deteriorate the radar detection performance is desired. Depending on the types of road structures, frequency components of the received signals have distinctive distributions. Focusing on this point, parameters that reflect statistical properties of each distribution are extracted. These parameters can be used as standards for the recognition because they show different values according to the road structures. For more enhanced recognition, we use a support vector machine method with a linear classifier or a Gaussian kernel, and the resulting confusion matrices are derived. According to the results, the proposed method successfully classifies the structures with high accuracy. If the recognition of the road structures that degrade radar's function is performed effectively, the safety of the driver in the radar-equipped vehicle can be ensured by applying additional signal processing or giving a warning message to the driver.

In this article, we propose a method to monitor traffic on the road using a 24.1 GHz radar system. In our work, we design our own traffic monitoring radar system from radar hardware, such as antenna systems and the transceiver, to radar software, such as detection and tracking algorithms. The radar we developed uses frequency-modulated continuous waveforms with a center frequency of 24.1 GHz, and its range resolution is tens of centimeters, which is enough to distinguish vehicles in multiple lanes. In addition, we can effectively distinguish vehicles by estimating their angles using an array antenna system. To evaluate the performance of our radar, we install it on the pedestrian overpass facing the road. From actual measurement results, our radar system can reliably estimate the distance to the vehicle, the speed of the vehicle, and the angle of the vehicle for a total of four lanes up to 300 m in real time. The traffic monitoring system using a radar sensor can compensate for the disadvantages of the camera-based road monitoring method.