IEEE International Radar Conference 

About: IEEE International Radar Conference is an academic conference. The conference publishes majorly in the area(s): Radar & Radar imaging. Over the lifetime, 3775 publications have been published by the conference receiving 23110 citations.

Waveform design principles for automotive radar systems

Abstract: This paper presents a high performance 77 GHz FMCW radar sensor for automotive applications. Powerful automotive radar systems are currently under development for various applications. Radar sensor based comfort systems like Adaptive Cruise Control (ACC) are already available on the market. The main objective from a radar sensor point of view is to detect all targets inside the observation area and estimate target range and relative velocity simultaneously with a high update rate. FMCW radar sensors have the advantages of very high range resolution but a serious task occurs in multiple target situations to suppress so-called ghost targets. In classical FMCW waveforms this has been solved in using multiple chirp signals with different slope. But in this case a long measurement time (approximately 50 ms) is needed which is a contradiction to a high update rate. Therefore, in this paper a new waveform design is presented which has all advantages of FMCW radars but needs an extremely low measurement time (10 ms) in a radar sensor with 3 different antenna beams.

Feature motivated polarization scattering matrix decomposition

Abstract: A method of decomposing the polarization scattering matrix into parts corresponding to nonreciprocal, asymmetric, and symmetric scatterers is presented. The decomposition is used to classify scattering matrices into one of eleven classes. The decomposition and classification scheme is applied to fully polarimetric, millimeter-wave measurement data. Results for a simple array of scatterers and for a truck are shown. >

Review of deep convolution neural network in image classification

Abstract: With the development of large data age, Convolutional neural networks (CNNs) with more hidden layers have more complex network structure and more powerful feature learning and feature expression abilities than traditional machine learning methods. The convolution neural network model trained by the deep learning algorithm has made remarkable achievements in many large-scale identification tasks in the field of computer vision since its introduction. This paper first introduces the rise and development of deep learning and convolution neural network, and summarizes the basic model structure, convolution feature extraction and pooling operation of convolution neural network. Then, the research status and development trend of convolution neural network model based on deep learning in image classification are reviewed, which is mainly introduced from the aspects of typical network structure construction, training method and performance. Finally, some problems in the current research are briefly summarized and discussed, and the new direction of future development is forecasted.