1-3hit |
Cheng-Chin CHIANG Chi-Lun HUANG
This paper presents the design of an automatic surveillance system to monitor the dangerous non-frontal gazes of the car driver. To track the driver's eyes, we propose a novel filter to locate the "between-eye", which is the middle point between the two eyes, to help the fast locating of eyes. We also propose a specially designed criterion function named mean ratio function to accurately locate the positions of eyes. To analyze the gazes of the driver, a multilayer perceptron neural network is trained to examine whether the driver is losing the proper gaze or not. By incorporating the neural network output with some well-designed alarm-issuing rules, the system performs the monitoring task for single dedicated driver and multiple different drivers with a satisfied performance in our experiments.
Chih-Kang HSU Wen-Kai TAI Cheng-Chin CHIANG Mau-Tsuen YANG
Visibility culling techniques have been studied extensively in computer graphics for interactive walkthrough applications in recent years. In this paper, a visibility culling approach by exploiting hardware-accelerated occlusion query is proposed. Organizing the regular grid representation of input scene as an octree-like hierarchy, a 2-tier view frustum culling algorithm is to efficiently cull away nodes invisible from a given viewpoint. Employing the eye-siding number of nodes, we can quickly enumerate an occlusion front-to-back order and effectively maximize the number of parallelizable occlusion queries for nodes while traversing the hierarchy. As experimental results show, our approach improves the overall performance in the test walkthrough.
JunWei HSIEH Cheng-Chin CHIANG
This paper presents an edge alignment method for stitching images when they have large displacements and light changes. First, without building any correspondences, the proposed method predicts all possible translation solutions by examining the consistency between edge positions. Then, the best solution can be obtained from the set of possible translations by a verification process. The proposed method has better capabilities to stitch images when they have large light changes and displacements. Since the method doesn't require building any correspondences or involve any optimization process, it performs more efficiently than other correlation techniques like feature-matching or phase-correlation approaches. Due to its simplicity and efficiency, different images can be very quickly aligned (less than 0.1 seconds) with the proposed method. Experimental results are provided to verify the superiority of the proposed method.