In this paper, we propose a method of generating a color image from light detection and ranging (LiDAR) 3D reflection intensity. The proposed method is composed of two steps: projection of LiDAR 3D reflection intensity into 2D intensity, and color image generation from the projected intensity by using a fully convolutional network (FCN). The color image should be generated from a very sparse projected intensity image. For this reason, the FCN is designed to have an asymmetric network structure, i.e., the layer depth of the decoder in the FCN is deeper than that of the encoder. The well-known KITTI dataset for various scenarios is used for the proposed FCN training and performance evaluation. Performance of the asymmetric network structures are empirically analyzed for various depth combinations for the encoder and decoder. Through simulations, it is shown that the proposed method generates fairly good visual quality of images while maintaining almost the same color as the ground truth image. Moreover, the proposed FCN has much higher performance than conventional interpolation methods and generative adversarial network based Pix2Pix. One interesting result is that the proposed FCN produces shadow-free and daylight color images. This result is caused by the fact that the LiDAR sensor data is produced by the light reflection and is, therefore, not affected by sunlight and shadow.
In this paper, a modified encoder-decoder structured fully convolutional network (ED-FCN) is proposed to generate the camera-like color image from the light detection and ranging (LiDAR) reflection image. Previously, we showed the possibility to generate a color image from a heterogeneous source using the asymmetric ED-FCN. In addition, modified ED-FCNs, i.e., UNET and selected connection UNET (SC-UNET), have been successfully applied to the biomedical image segmentation and concealed-object detection for military purposes, respectively. In this paper, we apply the SC-UNET to generate a color image from a heterogeneous image. Various connections between encoder and decoder are analyzed. The LiDAR reflection image has only 5.28% valid values, i.e., its data are extremely sparse. The severe sparseness of the reflection image limits the generation performance when the UNET is applied directly to this heterogeneous image generation. In this paper, we present a methodology of network connection in SC-UNET that considers the sparseness of each level in the encoder network and the similarity between the same levels of encoder and decoder networks. The simulation results show that the proposed SC-UNET with the connection between encoder and decoder at two lowest levels yields improvements of 3.87 dB and 0.17 in peak signal-to-noise ratio and structural similarity, respectively, over the conventional asymmetric ED-FCN. The methodology presented in this paper would be a powerful tool for generating data from heterogeneous sources.
Traffic light recognition is an essential task for an advanced driving assistance system (ADAS) as well as for autonomous vehicles. Recently, deep-learning has become increasingly popular in vision-based object recognition owing to its high performance of classification. In this study, we investigate how to design a deep-learning based high-performance traffic light detection system. Two main components of the recognition system are investigated: the color space of the input video and the network model of deep learning. We apply six color spaces (RGB, normalized RGB, Ruta’s RYG, YCbCr, HSV, and CIE Lab) and three types of network models (based on the Faster R-CNN and R-FCN models). All combinations of color spaces and network models are implemented and tested on a traffic light dataset with 1280×720 resolution. Our simulations show that the best performance is achieved with the combination of RGB color space and Faster R-CNN model. These results can provide a comprehensive guideline for designing a traffic light detection system.
Understanding of the aquifer hydraulic properties and hydrochemical characteristics of water is crucial for management plan and study skims in the target area, and flow motions and chemical species of groundwater are regarded as precious information on the geological history of the aquifers and the suitability of various usages. Cations and anions of groundwater are used to estimate the characteristics and origin of groundwater. In this study, we try to evaluate the quality of groundwater based on the comparison of the physiochemical characteristics and distribution of cations and anions in groundwater from rural areas. Therefore we focused on the evaluation of groundwater as some specific purposes such as agricultural and industrial use, general types of groundwater, lithological origin of chemical component in groundwater. In this point of view, major objectives of this study were grouped as following three categories: 1) quality assessment of groundwater as a special usage (agricultural, industrial); 2) determination of groundwater types; 3) tracing of ion sources of groundwater. The quality of agricultural water was evaluated using SAR, sodium (%), RSC, PI, SSP, MH, PS, and Kelly's ratio, and was classified as SAR (Excellent (100%)), Sodium ((Excellent (34%), Good (55%), Permissible (9%), Doubtful (1.6%), Unsuitable (0.4%)), RSC (Good (95.7%), Medium (3.5%), Bad (0.8%)), PI((Excellent (40.6%), Good (59%), Unsuitable (0.4%)), SSP ((Excellent (26.3%), Good (59.8%), Fair (13.1%), Poor (0.8%)), MH ((Acceptable (94.4%), Non-Acceptable (5.6%)), Kelly's Ratio ((Permissible (93%), NonPermissible (7%)), PS ((Excellent to Good (98%), Good to Injurious (1.2%), and Injurious to Unsatisfactory (0.2%)). Evaluation based on the Wilcox diagram was classified as "excellent to good" or "good to permissible", and the water quality evaluated using the U.S. salinity Laboratory's Diagram was classified as C1S1 (Excellent/Excellent) and C2S1 (Good/Excellent). And, in the applications of two factors of Langelier Saturation Index (LSI) and Corrosive ratio (CR), we could get similar results for defining the suitabilities of groundwater for the industrial purpose. And the groundwater samples were also clas- Ca -HCO + − type. And, estimation of dominance type (evaporation, rock, precipitation) based on the Gibbs diagram showed that the origin of anion and cation in groundwater are from the rock-do-minance, and the estimation of origin of anions using the Chadha diagram showed that the most of the ionic species was originated from the interactions between alkaline earths and alkali metals contained in the soil. And through the source-rock deduction followed by the comparison of Gibbs and Chadah diagram, it was shown that the chemical components in the groundwater were mostly induced from the water-rock deduction and major types of groundwater samples following the Chadah diagram were categorized such as following group types: dolomite type, gypsum type, alkaline and alkaline earth type.
As a component of organizational aggression, co-worker undermining erodes the well-being of the victims and the sustainability of the organization. Drawing on conservation of resources theory, this study identified the negative impact of co-worker undermining on the victim’s psychological capital, and empirically examined the influence of performance pressure as an antecedent and of authentic leadership as a moderator to suggest approaches to minimize this negative impact. A total of 485 subordinate employees from 10 organizations in South Korea completed a questionnaire survey. To prevent common method bias, the survey was designed to recruit participants from multiple organizations and was conducted in two waves. First, the results revealed that performance pressure had a positive relationship with the perception of co-worker’s undermining. Second, this perception of co-worker undermining had a negative influence on the victim’s psychological capital. Third, authentic leadership had the moderating effect of decreasing the negative relationship between co-worker undermining and psychological capital. Furthermore, authentic leadership moderated the mediating relationship between the performance pressure and psychological capital through co-worker’s undermining. These findings suggest that the level of performance pressure should be managed in advance so as not to reach excessive levels and the psychological capital of victims should be preserved through authentic leadership to minimize the negative impact of co-worker undermining.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.