“…Visual odometry, is a smaller subset which doesn't involve structural estimation, but just camera motion estimation. These approaches could either be sparse [10,25,27,30,32], semi-dense [7,8] or dense [2,33]. The main issue that arises in these methods is that of improper correspondences in texture-less areas, or if there are occlusions or repeating patterns.…”
Deep approaches to predict monocular depth and ego-motion have grown in recent years due to their ability to produce dense depth from monocular images. The main idea behind them is to optimize the photometric consistency over image sequences by warping one view into another, similar to direct visual odometry methods. One major drawback is that these methods infer depth from a single view, which might not effectively capture the relation between pixels. Moreover, simply minimizing the photometric loss does not ensure proper pixel correspondences, which is a key factor for accurate depth and pose estimations.In contrast, we propose a 2-view depth network to infer the scene depth from consecutive frames, thereby learning inter-pixel relationships. To ensure better correspondences, thereby better geometric understanding, we propose incorporating epipolar constraints to make the learning more geometrically sound. We use the Essential matrix obtained using Nistér's Five Point Algorithm, to enforce meaningful geometric constraints, rather than using it as training labels. This allows us to use lesser no. of trainable parameters compared to state-of-the-art methods. The proposed method results in better depth images and pose estimates, which capture the scene structure and motion in a better way. Such a geometrically constrained learning performs successfully even in cases where simply minimizing the photometric error would fail.
“…Visual odometry, is a smaller subset which doesn't involve structural estimation, but just camera motion estimation. These approaches could either be sparse [10,25,27,30,32], semi-dense [7,8] or dense [2,33]. The main issue that arises in these methods is that of improper correspondences in texture-less areas, or if there are occlusions or repeating patterns.…”
Deep approaches to predict monocular depth and ego-motion have grown in recent years due to their ability to produce dense depth from monocular images. The main idea behind them is to optimize the photometric consistency over image sequences by warping one view into another, similar to direct visual odometry methods. One major drawback is that these methods infer depth from a single view, which might not effectively capture the relation between pixels. Moreover, simply minimizing the photometric loss does not ensure proper pixel correspondences, which is a key factor for accurate depth and pose estimations.In contrast, we propose a 2-view depth network to infer the scene depth from consecutive frames, thereby learning inter-pixel relationships. To ensure better correspondences, thereby better geometric understanding, we propose incorporating epipolar constraints to make the learning more geometrically sound. We use the Essential matrix obtained using Nistér's Five Point Algorithm, to enforce meaningful geometric constraints, rather than using it as training labels. This allows us to use lesser no. of trainable parameters compared to state-of-the-art methods. The proposed method results in better depth images and pose estimates, which capture the scene structure and motion in a better way. Such a geometrically constrained learning performs successfully even in cases where simply minimizing the photometric error would fail.
“…A spinoff of this problem comes under the domain of Visual SLAM or VO, which involves real-time estimation of camera poses and/or a structural 3D map of the environment. There approaches could be either sparse [34,29,13,32,27], semi-dense [11,10] or dense [35,2]. Both methods suffer from the same sets of problems, namely improper correspondences in texture-less areas, or if there are occlusions or repeating patterns.…”
Most geometric approaches to monocular Visual Odometry (VO) provide robust pose estimates, but sparse or semidense depth estimates. Off late, deep methods have shown good performance in generating dense depths and VO from monocular images by optimizing the photometric consistency between images. Despite being intuitive, a naive photometric loss does not ensure proper pixel correspondences between two views, which is the key factor for accurate depth and relative pose estimations. It is a well known fact that simply minimizing such an error is prone to failures.We propose a method using Epipolar constraints to make the learning more geometrically sound. We use the Essential matrix, obtained using Nistér's Five Point Algorithm, for enforcing meaningful geometric constraints on the loss, rather than using it as labels for training. Our method, although simplistic but more geometrically meaningful, using lesser number of parameters, gives a comparable performance to state-of-the-art methods which use complex losses and large networks showing the effectiveness of using epipolar constraints. Such a geometrically constrained learning method performs successfully even in cases where simply minimizing the photometric error would fail.
“…Edge based Visual Odometry: Tarrio and Pedre [13] present an edge-based visual odometry pipeline that uses edges as a feature for depth estimation. But camera estimation is erroneous because odometry works only on pairwise consistency, global consistency checking is very important for accurate camera estimation in a long trajectory.…”
Section: Related Workmentioning
confidence: 99%
“…We thin [18] the DoG edges further to generate edges of a single pixel width. We apply an edge filtering process described by Juan and Sol [13] upon the thinned edges to calculate connectivity of the edge points. This point connectivity information plays an important role in validating edge continuation in different stages of our Edge SLAM pipeline.…”
Visual SLAM shows significant progress in recent years due to high attention from vision community but still, challenges remain for low-textured environments. Feature based visual SLAMs do not produce reliable camera and structure estimates due to insufficient features in a low-textured environment. Moreover, existing visual SLAMs produce partial reconstruction when the number of 3D-2D correspondences is insufficient for incremental camera estimation using bundle adjustment. This paper presents Edge SLAM, a feature based monocular visual SLAM which mitigates the above mentioned problems. Our proposed Edge SLAM pipeline detects edge points from images and tracks those using optical flow for point correspondence. We further refine these point correspondences using geometrical relationship among three views. Owing to our edge-point tracking, we use a robust method for two-view initialization for bundle adjustment. Our proposed SLAM also identifies the potential situations where estimating a new camera into the existing reconstruction is becoming unreliable and we adopt a novel method to estimate the new camera reliably using a local optimization technique. We present an extensive evaluation of our proposed SLAM pipeline with most popular open datasets and compare with the state-of-the art. Experimental result indicates that our Edge SLAM is robust and works reliably well for both textured and less-textured environment in comparison to existing state-of-the-art SLAMs.
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.