The Deep Q-Network (DQN) is one of the key methods in the deep reinforcement learning algorithm, which has a deep neural network structure used to estimate Q -values in Q-learning methods. We have previously implemented a simulation system considering DQN for control of actuator nodes in Wireless Sensor and Actuator Networks (WSANs). In addition, we have designed and implemented a DQN based Autonomous Aerial Vehicle (AAV) testbed . In this paper, we propose and evaluate a Tabu List Strategy based DQN (TLS-DQN) for AAV mobility control. For evaluation, we compared the simulation results of the mobility control of AAV in indoor single-path environment using normal DQN and the TLS-DQN. The simulation results show that the TLS-DQN has a better performance than the normal DQN.

A Tabu list strategy based DQN for AAV mobility in indoor single-path environment: Implementation and performance evaluation

In this paper, we propose a color image enhancement method that uses the CIELAB color space to improve the quality of degraded images for human visual perception. In our method, the lightness of a color image is enhanced, based on gamma correction, and the hue and chroma are preserved in the CIELAB color space. During this process, color gamut problem may occur while inversely converting the enhanced CIELAB color components to the RGB color space. Therefore, we introduce a color gamut adjustment to cope with this problem. In the color gamut adjustment, the chroma is changed while preserving the enhanced lightness and the hue so that the inversely converted CIELAB color components will exist inside the color gamut of the RGB color space. To illustrate the effectiveness of this method, experiments, using several digital images, are conducted.

Hue-preserving image enhancement in CIELAB color space considering color gamut

The Deep Q-Network (DQN) is one of the deep reinforcement learning algorithms, which uses deep neural network structure to estimate the Q-value in Q-learning. In the previous work, we designed and implemented a DQN-based Autonomous Aerial Vehicle (AAV) testbed and proposed a Tabu List Strategy based DQN (TLS-DQN). In this paper, we propose a LiDAR Based Mobile Area Decision Method for TLS-DQN to improve the control for AAV Mobility. The evaluation results show that the proposed method makes a good decision for the destination and mobile area based on LiDAR.

A LiDAR Based Mobile Area Decision Method for TLS-DQN: Improving Control for AAV Mobility

The Deep Q-Network (DQN) is one of the deep reinforcement learning algorithms, which uses deep neural network structure to estimate the Q-value in Q-learning. In the previous work, we designed and implemented a DQN-based Autonomous Aerial Vehicle (AAV) testbed and proposed a Tabu List Strategy based DQN (TLS-DQN). In this paper, we consider corner environment as a new simulation scenario and carried out simulations for normal DQN and TLS-DQN for mobility control of AAV. Simulation results show that TLS-DQN performs better than normal DQN in the corner environment.

Simulation Results of a DQN Based AAV Testbed in Corner Environment: A Comparison Study for Normal DQN and TLS-DQN.

Color transfer is to generate synthetic images by changing the color of target images with new colors obtained from given source images, while the geometrical structure of the synthetic images remains the same. Classical color transfer models use a total variation (TV) regularizer to preserve the details and suppress the noise of the synthetic images. These models can sometimes cause staircase effect and geometrical structure details over-smoothed. To overcome these problems, we propose a new color transfer model in which an adaptive second-order total generalized variation (TGV) regularizer is designed. Here, the adaptive second-order TGV regularizer is a weighted second-order TGV regularizer. The weight is computed by an adaptive edge indicator function. In addition, an efficient algorithm is developed to program our new model. The algorithm is based on a weighted primal–dual method. Experimental results and comparisons demonstrate that our new color transfer model can generate better results than classical TV regularizer-based models in the aspects of the inhibition of staircase effect and the preservation of image details.

Color Transfer Using Adaptive Second-Order Total Generalized Variation Regularizer

Ambient Intelligence (AmI) deals with a new world of ubiquitous computing devices, where physical environments interact intelligently and unobtrusively with people. AmI environments can be diverse, such as homes, offices, meeting rooms, schools, hospitals, control centers, vehicles, tourist attractions, stores, sports facilities, and music devices. This paper presents design and implementation of a simulation system based on Deep Q-Network (DQN) for actuation decision in AmI. DQN is a deep neural network structure used for estimation of Q-value of the Q-learning method. We implemented the proposed simulating system by Rust programming language. We describe the design and implementation of the simulation system, and show some simulation results to evaluate its performance.

Design of a Deep Q-Network Based Simulation System for Actuation Decision in Ambient Intelligence.

Food Image Enhancement by Adjusting Intensity and Saturation in RGB Color Space

Color transfer originally proposed by Reinhard et al. is a method to change the color appearance of an input image by using the color information of a reference image. The purpose of this study is to modify color transfer so that it works well even when the scenes of the input and reference images are not similar. Concretely, a color transfer method with lightness correction and color gamut adjustment is proposed. The lightness correction is applied to preserve the perceived lightness which is explained by the Helmholtz–Kohlrausch (H–K) effect. This effect is the phenomenon that vivid colors are perceived as brighter than dull colors with the same lightness. Hence, when the chroma is changed by image processing, the perceived lightness is also changed even if the physical lightness is preserved after the image processing. In the proposed method, by considering the H–K effect, color transfer that preserves the perceived lightness after processing is realized. Furthermore, color gamut adjustment is introduced to address the color gamut problem, which is caused by color space conversion. The effectiveness of the proposed method is verified by performing some experiments.

Color transfer method preserving perceived lightness

It is known that the lenticular transmittance of elderly people is lower than that of young people. Especially, it is remarkable for short wavelength lights. Therefore blue-tinged colors become darker comparing with the other colors in the field of vision of elderly people. In this paper, in order to improve the visibilities of blue-tinged colors in the elderly vision, the data-dependent gamma correction is proposed. Concretely, RGB components are converted by the gamma correction with a gamma which is set according to the hue, saturation and lightness contrast in each pixel. Through the experiments using some digital color images, the effectiveness of the proposed method is verified.

Gamma correction-based image enhancement for elderly vision

The color of an object appears to be different for elderly and young persons. This is because human visual features vary with on age. In general, the spectral transmittance of the crystalline lens of an elderly person is lower than that of a young person. The low spectral transmittance decreases the brightness of the visual field. This phenomenon affects the color appearance of an image in human visual perception. In this paper, a lightness transform method is proposed to improve the color appearance of images for elderly persons. In the proposed method, colors that are difficult for an elderly person to see are transformed into colors that are easy to see by adding lightness contrast. The performance of the proposed method is confirmed in experiments using digital images.

Chiaki Ueda

Papers

Design of a Deep Q-Network Based Simulation System for Actuation Decision in Ambient Intelligence.

Food Image Enhancement by Adjusting Intensity and Saturation in RGB Color Space

Color transfer method preserving perceived lightness

Gamma correction-based image enhancement for elderly vision

Improvement in appearance of colors for elderly persons using lightness transform