Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
5 results
Search Results
Item Entropy-difference based stereo error detection(Institute of Electrical and Electronics Engineers Inc., 2016) Mukherjee, S.; Cheng, I.; Guddeti, G.R.; Basu, A.Stereo depth estimation is error-prone; hence, effective error detection methods are desirable. Most such existing methods depend on characteristics of the stereo matching cost curve, making them unduly dependent on functional details of the matching algorithm. As a remedy, we propose a novel error detection approach based solely on the input image and its depth map. Our assumption is that, entropy of any point on an image will be significantly higher than the entropy of its corresponding point on the image's depth map. In this paper, we propose a confidence measure, Entropy-Difference (ED) for stereo depth estimates and a binary classification method to identify incorrect depths. Experiments on the Middlebury dataset show the effectiveness of our method. Our proposed stereo confidence measure outperforms 17 existing measures in all aspects except occlusion detection. Established metrics such as precision, accuracy, recall, and area-under-curve are used to demonstrate the effectiveness of our method. © 2016 IEEE.Item Depth-Based Selective Blurring in Stereo Images Using Accelerated Framework(3D Research Center 3drc@kw.ac.kr, 2014) Mukherjee, S.; Guddeti, R.M.R.Abstract: We propose a hybrid method for stereo disparity estimation by combining block and region-based stereo matching approaches. It generates dense depth maps from disparity measurements of only 18 % image pixels (left or right). The methodology involves segmenting pixel lightness values using fast K-Means implementation, refining segment boundaries using morphological filtering and connected components analysis; then determining boundaries’ disparities using sum of absolute differences (SAD) cost function. Complete disparity maps are reconstructed from boundaries’ disparities. We consider an application of our method for depth-based selective blurring of non-interest regions of stereo images, using Gaussian blur to de-focus users’ non-interest regions. Experiments on Middlebury dataset demonstrate that our method outperforms traditional disparity estimation approaches using SAD and normalized cross correlation by up to 33.6 % and some recent methods by up to 6.1 %. Further, our method is highly parallelizable using CPU–GPU framework based on Java Thread Pool and APARAPI with speed-up of 5.8 for 250 stereo video frames (4,096 × 2,304). © 2014, 3D Research Center, Kwangwoon University and Springer-Verlag Berlin Heidelberg.Item AMMDAS: Multi-modular generative masks processing architecture with adaptive wide field-of-view modeling strategy(Institute of Electrical and Electronics Engineers Inc., 2020) Desanamukula, V.S.; Chilukuri, P.K.; Padala, P.; Padala, P.; Pvgd, P.R.The usage of transportation systems is inevitable; any assistance module which can catalyze the flow involved in transportation systems, parallelly improving the reliability of processes involved is a boon for day-to-day human lives. This paper introduces a novel, cost-effective, and highly responsive Post-active Driving Assistance System, which is "Adaptive-Mask-Modelling Driving Assistance System" with intuitive wide field-of-view modeling architecture. The proposed system is a vision-based approach, which processes a panoramic-front view (stitched from temporal synchronous left, right stereo camera feed) & simple monocular-rear view to generate robust & reliable proximity triggers along with co-relative navigation suggestions. The proposed system generates robust objects, adaptive field-of-view masks using FRCNN+Resnet-101_FPN, DSED neural-networks, and are later processed and mutually analyzed at respective stages to trigger proximity alerts and frame reliable navigation suggestions. The proposed DSED network is an Encoder-Decoder-Convolutional-Neural-Network to estimate lane-offset parameters which are responsible for adaptive modeling of field-of-view range (1570-2100) during live inference. Proposed stages, deep-neural-networks, and implemented algorithms, modules are state-of-the-art and achieved outstanding performance with minimal loss(L{p, t}, L?, LTotal) values during benchmarking analysis on our custom-built, KITTI, MS-COCO, Pascal-VOC, Make-3D datasets. The proposed assistance-system is tested on our custom-built, multiple public datasets to generalize its reliability and robustness under multiple wild conditions, input traffic scenarios & locations. © 2020 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.Item L, r-Stitch Unit: Encoder-Decoder-CNN Based Image-Mosaicing Mechanism for Stitching Non-Homogeneous Image Sequences(Institute of Electrical and Electronics Engineers Inc., 2021) Chilukuri, P.K.; Padala, P.; Padala, P.; Desanamukula, V.S.; Pvgd, P.R.Image-stitching (or) mosaicing is considered an active research-topic with numerous use-cases in computer-vision, AR/VR, computer-graphics domains, but maintaining homogeneity among the input image sequences during the stitching/mosaicing process is considered as a primary-limitation major-disadvantage. To tackle these limitations, this article has introduced a robust and reliable image stitching methodology (l,r-Stitch Unit), which considers multiple non-homogeneous image sequences as input to generate a reliable panoramically stitched wide view as the final output. The l,r-Stitch Unit further consists of a pre-processing, post-processing sub-modules a l,r-PanoED-network, where each sub-module is a robust ensemble of several deep-learning, computer-vision image-handling techniques. This article has also introduced a novel convolutional-encoder-decoder deep-neural-network (l,r-PanoED-network) with a unique split-encoding-network methodology, to stitch non-coherent input left, right stereo image pairs. The encoder-network of the proposed l,r-PanoED extracts semantically rich deep-feature-maps from the input to stitch/map them into a wide-panoramic domain, the feature-extraction feature-mapping operations are performed simultaneously in the l,r-PanoED's encoder-network based on the split-encoding-network methodology. The decoder-network of l,r-PanoED adaptively reconstructs the output panoramic-view from the encoder networks' bottle-neck feature-maps. The proposed l,r-Stitch Unit has been rigorously benchmarked with alternative image-stitching methodologies on our custom-built traffic dataset and several other public-datasets. Multiple evaluation metrics (SSIM, PSNR, MSE, L_{\alpha,\beta,\gamma } , FM-rate, Average-latency-time) wild-Conditions (rotational/color/intensity variances, noise, etc) were considered during the benchmarking analysis, and based on the results, our proposed method has outperformed among other image-stitching methodologies and has proved to be effective even in wild non-homogeneous inputs. © 2013 IEEE.Item Demonstration of structure-from-motion (SfM) and multi-view stereo (MVS) close range photogrammetry technique for scour hole analysis(Springer, 2021) Mali, V.K.; Venu, P.; Nagaraj, M.K.; Kuiry, S.N.Comprehensive data collection remains a challenge in the field of sediment research. The manual acquisition of fine-gridded data is almost infeasible even for a laboratory setup. Therefore, this paper demonstrates a simple and cost-effective SfM–MVS technique to acquire accurate morphological data. This data further can be used for assessing the scour development around a bridge pier. For this purpose, the experiments are conducted for clear-water scour around circular and hexagonal piers for three different discharges. Before the start of the experimental run, a set of overlapped images is taken using the digital camera. Once the experiment run is completed, the water in the flume is completely drained off and then again another set of overlapped photos are taken. A total of eight ground control points (GCPs) is used to transform the generated relative three-dimensional cloud points to the absolute local coordinate system. Eventually, the high-spatial resolution digital elevation models (DEMs) are generated using the SfM–MVS photogrammetry technique. A statistical analysis is performed between the checkpoints (observed data) and DEM predicted points, which revealed that the generated DEMs show high accuracy in all the cases. It is therefore concluded that the SfM–MVS technique can be applied to understand the morghological changes around any shape of the piers. Thus, the proposed image analysis method can be adopted for obtaining the high spatial resolution data for sediment transport research. © 2021, Indian Academy of Sciences.