Browsing by Author "Chen, Yung-Yao"

Now showing 1 - 4 of 4

Domain Adaptation With Foreground/Background Cues and Gated Discriminators
(2020-07-01)
Lin, Yong-Xiang
;
Tan, Daniel Stanley
;
Chen, Yung-Yao
;
Huang, Ching-Chun
;
Hua, Kai-Lung
Self-driving cars leverage on semantic segmentation to understand an urban scene. However, it is costly to collect segmentation labels, thus, synthetic datasets are used to train segmentation models. Unfortunately, the synthetic to real domain shift causes these models to perform poorly. Prior works use adversarial training to align features of both synthetic and real-world images. We observe that background objects tend to be similar across domains, while foreground objects tend to have more variations. Using this insight, we propose an adaptation method that uses foreground and background cues and adapt them separately. We also propose a mask-aware gated discriminator that learns soft masks from the input foreground and background masks instead of naively performing binary masking that immediately removes information outside of the predicted masks. We evaluate our method on two different datasets and show that our method outperforms several state-of-the-art baselines, which verifies the effectiveness of our approach.
Reversible AMBTC-Based Data Hiding With Security Improvement by Chaotic Encryption
(2019-01-01)
Wang, Hsiang-Ying
;
Lin, Hsin-Ju
;
Gao, Xiang-Yun
;
Cheng, Wen-Huang
;
Chen, Yung-Yao
Social networking and cloud computing are being extensively used, and in this era, the frequency of sending information or images to each other is increasing. The prevention of private information leakage during communication over the Internet has become a concern in the past decades. Several data protection methods, such as cryptographic, watermarking, and steganography techniques, have been proposed to protect private data. In this paper, an embedding method is proposed based on an absolute moment block truncation coding (AMBTC)-compressed image. High and low mean tables are extracted from a compressed image and are divided into non-overlapping blocks. An adaptive variable N-bit bit plane truncation image embedding method is proposed to embed the secret data in each block. In this method, at the receiver end, the secret data are extracted, and the original AMBTC image could be recovered by recalling the stored peak and zero points. In addition, a chaotic encryption scheme is integrated into the proposed system to improve robustness against security vulnerability. The results show that the proposed method has superior performance and higher payload compared with the reference methods.
SPATIALLY-AWARE DOMAIN ADAPTATION FOR SEMANTIC SEGMENTATION OF URBAN SCENES
(2019-01-01)
Lin, Yong-Xiang
;
Tan, Daniel Stanley
;
Cheng, Wen-Huang
;
Chen, Yung-Yao
;
Hua, Kai-Lung
It is very expensive and time consuming to collect a large enough dataset with pixel-level annotations to train a semantic segmentation model. Synthetic datasets are common alternatives for training segmentation models, however models trained on synthetic data do not necessarily perform well on real world images due to the domain shift problem. Domain adaptation techniques address this problem by leveraging on adversarial training to align features. Prior works have mostly performed global feature alignment. They do not consider the positions of objects. However, objects in urban scenes are highly correlated with their spatial locations. For example, the sky will always appear on top while cars will usually appear in the middle of the image. Based on this insight, we propose a spatial-aware discriminator that accounts for the spatial prior on the objects in order to improve the feature alignment. We demonstrate in our experiments that our model outperforms several state-of-the-art baselines in terms of mean intersection over union (mIoU).
VEHICLE DETECTION IN THERMAL IMAGES USING DEEP NEURAL NETWORK
(2018-01-01)
Chang, Chin-Wei
;
Srinivasan, Kathiravan
;
Chen, Yung-Yao
;
Cheng, Wen-Huang
;
Hua, Kai-Lung
In today's world, it becomes critical for a self-driving car to detect the vehicles irrespective of it being a day or night. We propose a real-time vehicle detection using a sequence of night-time thermal images. Moreover, the thermal images have the capability of retaining even the minuscule vehicle details in a dim environment. For an efficient vehicle detection, the thermal image dataset collected during the dusk and night is used for training purposes. Subsequently, the contrast enhancement and sharpening of these images are performed using the Thermal Feature Enhancement (TFE). Then the concatenated images are supplied as the input to allow the model to learn more effectively. Besides, we also propose an improved convolution network model entitled as the Thermal Image Only Looked Once (TOLO) model for vehicle detection. Additionally, we propose a method called as Low Probability Candidate Filter (LPCF) to compensate the probability of not-easy-to-detect vehicles. Our proposed method produces better results for the F1-measure in comparison with existing methods.