Browsing by Author "Ardianto, Sandy"

Now showing 1 - 3 of 3

Multi-View and Multi-Modal Action Recognition with Learned Fusion
(2018-01-01)
Ardianto, Sandy
;
Hang, Hsueh-Ming
;
電機學院
;
College of Electrical and Computer Engineering
In this paper, we study multi-modal and multi-view action recognition system based on the deep-learning techniques. We extended the Temporal Segment Network with additional data fusion stage to combine information from different sources. In this research, we use multiple types of information from different modality such as RGB, depth, infrared data to detect predefined human actions. We tested various combinations of these data sources to examine their impact on the final detection accuracy. We designed 3 information fusion methods to generate the final decision. The most interested one is the Learned Fusion Net designed by us. It turns out the Learned Fusion structure has the best results but requires more training.
NCTU-GTAV360: A 360 degrees Action Recognition Video Dataset
(2019-01-01)
Ardianto, Sandy
;
Hang, Hsueh-Ming
;
電機學院
;
College of Electrical and Computer Engineering
Despite many action recognition video datasets available right now, none of them are in the spherical projection. NCTU-GTAV360 is a new 360 degrees action recognition video dataset captured from a game, Grand Theft Auto V (GTA V). The spherical video is obtained by stitching 24 views from various angles and combining them into a video. The benefit of using 360 degrees cameras is that it can capture the entire surroundings using one single camera. We captured 200 locations within the Los Santos city (city name in the GTA V). This dataset should benefit researchers working on the spherical images, particularly the human action recognition research using machine learning or deep learning technique, which requires a large amount of training data and the associated ground-truth.
Real-Time Traffic Sign Recognition using Color Segmentation and SVM
(2017-01-01)
Ardianto, Sandy
;
Chen, Chih-Jung
;
Hang, Hsueh-Ming
;
電機學院
;
College of Electrical and Computer Engineering
Traffic Sign Recognition (TSR) that can automatically notify and warn a vehicle driver is an essential element in the Advanced Driver Assistance System. In this study, we design and implement a real time traffic sign recognition system implemented on Advantech ARK-2121, a small computer mounted on car. The entire process is divided into two parts, the detection step and the classification step. In the detection step, we adopt color filtering, Laplacian and Gaussian filter to enhance an acquired image. Then, we detect the sign based on the contours. The recognition algorithm is accelerated by dividing an input frame into multiple blocks and process them in parallel. We improve the detection accuracy by enhancing input image before the recognition step. The SVM and HOG features are the major techniques in the recognition step. Our detection accuracy is around 91% and the classification accuracy is higher than 98% on the average.