Capsule Neural Network based Height Classification using Low-Cost Automotive Ultrasonic Sensors
High performance ultrasonic sensor hardware is mainly used in medical applications. Although, the development in automotive scenarios is towards autonomous driving, the ultrasonic sensor hardware still stays low-cost and low-performance, respectively. To overcome the strict hardware limitations, we propose to use capsule neural networks. By the high classification capability of this network architecture, we can achieve outstanding results for performing a detailed height analysis of detected objects. We apply a novel resorting and reshaping method to feed the neural network with ultrasonic data. This increases classification performance and computation speed. We tested the approach under different environmental conditions to verify that the proposed method is working independent of external parameters that is needed for autonomous driving.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingClassificationGeneral ClassificationSimilar Papers 제목 키워드 기반
Realistic Ultrasonic Environment Simulation Using Conditional Generative Adversarial Networks
Recently, realistic data augmentation using neural networks especially generative neural networks (GAN) has achieved outstanding results. The communities main research focus is visual image processing. However, automotiv…
Data AugmentationA deep learning approach for direction of arrival estimation using automotive-grade ultrasonic sensors
In this paper, a deep learning approach is presented for direction of arrival estimation using automotive-grade ultrasonic sensors which are used for driving assistance systems such as automatic parking. A study and impl…
Direction of Arrival EstimationFMCW Radar Height Estimation of Moving Vehicles by Analyzing Multipath Reflections
Target classification is an important task of automotive radar systems. In this work, a concept for estimating the height of vehicles to allow for a differentiation between passenger cars, trucks, and others, is presente…
Real-time video streaming in vivo using ultrasound as the communication channel
The emergence of capsule endoscopy has provided a means of capturing video of the small intestines without having to resort to an invasive procedure involving intubation. However, real-time video streaming to a receiver …
WeldMon: A Cost-effective Ultrasonic Welding Machine Condition Monitoring System
Ultrasonic welding machines play a critical role in the lithium battery industry, facilitating the bonding of batteries with conductors. Ensuring high-quality welding is vital, making tool condition monitoring systems es…
ClassificationData Augmentation