Traffic sign recognition is a very important function in automatic driving assistance systems (ADAS). This study addresses the design and implementation of a vision-based ADAS based on an image-based speed-limit sign ...
详细信息
Traffic sign recognition is a very important function in automatic driving assistance systems (ADAS). This study addresses the design and implementation of a vision-based ADAS based on an image-based speed-limit sign (SLS) recognition algorithm, which can automatically detect and recognise SLS on the road in real-time. To improve the recognition rate of SLS having different orientations and scales in the image, this study also presents a new sign content description algorithm, which describes the detected road sign using centroid-to-contour (CtC) distances of the extracted sign content. The proposed CtC descriptor is robust to translation, rotation and scale changes of the SLS in the image. This advantage improves the recognition accuracy of a support vector machine classifier trained using a large database of traffic signs. The proposed SLS recognition method had been implemented on two different embedded platforms, each of them equipped with an ARM-based Quad-Core CPU running Android 4.4 operating system. Experimental results validate that the proposed method not only provides a high recognition rate, but also achieves real-time performance up to 30 frames per second for processing 1280x720 video streams running on a commercial ARM-based smartphone.
Parameter estimation problems can be nonlinear, even if the dynamics are expressed by a linear model. The extended Kalman filter (EKF), even though it is one of the most popular nonlinear estimation techniques, may no...
详细信息
Parameter estimation problems can be nonlinear, even if the dynamics are expressed by a linear model. The extended Kalman filter (EKF), even though it is one of the most popular nonlinear estimation techniques, may not converge without sufficient a priori information. This paper utilizes a globally convergent nonlinear estimation method the double Kalman filter (DKF) for a vibrating cantilever beam. A globally valid linear time-varying (LTV) model is required by the first stage of the DKF depending on some conditions on input and output excitation. Without considering noise, this LW model provides the first stage and is globally equivalent to the nonlinear system. Since the neglected input and output noises can degrade the quality of estimation, the second stage linearizes the nonlinear dynamics, utilizing the nominally globally convergent estimate of the first stage, and improves the quality of estimation. Both estimation methods were applied to a cantilever beam setup in real-time. An adaptive linear quadratic regulator utilizes the estimated parameters to attenuate unknown transient disturbances. Different scenarios have been explored, providing a fair comparison between EKF and DKF. These methods have been implemented on an embedded ARM-based microcontroller unit and illustrates improved convergent properties of the DKF over the EKF. The global stability of the DKF is verified and it has been observed that it needs twice the computational cost of the EKF. (C) 2018 Elsevier Ltd. All rights reserved.
Automatic recognition of the eye states is essential for diverse computer vision applications related to drowsiness detection, facial emotion recognition (FER), human-computer interaction (HCI), etc. Existing solution...
详细信息
Automatic recognition of the eye states is essential for diverse computer vision applications related to drowsiness detection, facial emotion recognition (FER), human-computer interaction (HCI), etc. Existing solutions for eye state detection are either parameter intensive or suffer from a low recognition rate. This paper presents the design and implementation of a vision-based system for real-time eye state recognition on a resource-constrained embedded platform to tackle these issues. The designed system uses an ensemble of two lightweight convolutional neural networks (CNN), each trained to extract relevant information from the eye patches. We adopted transfer-learning-based fine-tuning to overcome the over-fitting issues when training the CNNs on small sample eye state datasets. Once trained, these CNNs are integrated and jointly fine-tuned to achieve enhanced performance. Experimental results manifest the effectiveness of the proposed eye state recognizer that is robust and computationally efficient. On the ZJU dataset, the proposed DCNNE model delivered the state-of-the-art recognition accuracy of 97.99% and surpassed the prior best recognition accuracy of 97.20% by 0.79%. The designed model also achieved competitive results on the CEW and MRL datasets. Finally, the designed CNNs are optimized and ported on two different embedded platforms for real-world applications with real-time performance. The complete system runs at 62 frames per second (FPS) on an Nvidia Xavier device and 11 FPS on a low-cost Intel NCS2 embedded platform using a frame size of 640 x 480 pixels resolution.
暂无评论