Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Computer Engineering
Past To Present (P2p): Road Thermal Image Colorization, Yuseong Park
Past To Present (P2p): Road Thermal Image Colorization, Yuseong Park
Electronic Theses and Dissertations
Thermal image colorization into realistic RGB image is a challenging task. Thermal cameras are easily to detect objects in particular situation (e.g. darkness and fog) that the human eyes cannot detect. However, it is difficult to interpret the thermal image with human eyes. Enhancing thermal image colorization is an important task to improve these areas. The results of the existing colorization method still have color ambiguities, distortion, and blurriness problems. This paper focused on thermal image colorization using pix2pix network architecture based on Generative Adversarial Net (GAN). Pix2pix is a model that transforms thermal image into RGB image, but our …
Kernel-Controlled Dqn Based Cnn Pruning For Model Compression And Acceleration, Romancha Khatri
Kernel-Controlled Dqn Based Cnn Pruning For Model Compression And Acceleration, Romancha Khatri
Electronic Theses and Dissertations
Apart from the accuracy, the size of convolutional neural networks (CNN) models is another principal factor for facilitating the deployment of models on memory, power and budget constrained devices. However, conventional model compression techniques require human experts to setup parameters to explore the design space which is suboptimal and time consuming. Various pruning techniques are implemented to gain compression, trading off speed and accuracy. Given a CNN model [11], we propose an automated deep reinforcement learning [9] based model compression technique that can effectively turned off kernels on each layer by observing its significance on decision making. By observing accuracy, …
Semantic Segmentation Using Modified U-Net Architecture For Crack Detection, Michael Sun
Semantic Segmentation Using Modified U-Net Architecture For Crack Detection, Michael Sun
Electronic Theses and Dissertations
The visual inspection of a concrete crack is essential to maintaining its good condition during the service life of the bridge. The visual inspection has been done manually by inspectors, but unfortunately, the results are subjective. On the other hand, automated visual inspection approaches are faster and less subjective. Concrete crack is an important deficiency type that is assessed by inspectors. Recently, various Convolutional Neural Networks (CNNs) have become a prominent strategy to spot concrete cracks mechanically. The CNNs outperforms the traditional image processing approaches in accuracy for the high-level recognition task. Of them, U-Net, a CNN based semantic segmentation …