BoMuDANet: Unsupervised Adaptation for Visual Scene Understanding in Unstructured Driving Environments

• URL: http://arxiv.org/abs/2010.03523v3
• Date: Sun, 23 May 2021 15:27:04 GMT
• Title: BoMuDANet: Unsupervised Adaptation for Visual Scene Understanding in Unstructured Driving Environments
• Authors: Divya Kothandaraman, Rohan Chandra, Dinesh Manocha
• Abstract summary: We present an unsupervised adaptation approach for visual scene understanding in unstructured traffic environments. Our method is designed for unstructured real-world scenarios with dense and heterogeneous traffic consisting of cars, trucks, two-and three-wheelers, and pedestrians.
• Score: 54.22535063244038
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present an unsupervised adaptation approach for visual scene understanding in unstructured traffic environments. Our method is designed for unstructured real-world scenarios with dense and heterogeneous traffic consisting of cars, trucks, two-and three-wheelers, and pedestrians. We describe a new semantic segmentation technique based on unsupervised domain adaptation (DA), that can identify the class or category of each region in RGB images or videos. We also present a novel self-training algorithm (Alt-Inc) for multi-source DA that improves the accuracy. Our overall approach is a deep learning-based technique and consists of an unsupervised neural network that achieves 87.18% accuracy on the challenging India Driving Dataset. Our method works well on roads that may not be well-marked or may include dirt, unidentifiable debris, potholes, etc. A key aspect of our approach is that it can also identify objects that are encountered by the model for the fist time during the testing phase. We compare our method against the state-of-the-art methods and show an improvement of 5.17% - 42.9%. Furthermore, we also conduct user studies that qualitatively validate the improvements in visual scene understanding of unstructured driving environments.

Related papers

• Neural Semantic Map-Learning for Autonomous Vehicles [85.8425492858912]
  We present a mapping system that fuses local submaps gathered from a fleet of vehicles at a central instance to produce a coherent map of the road environment. Our method jointly aligns and merges the noisy and incomplete local submaps using a scene-specific Neural Signed Distance Field. We leverage memory-efficient sparse feature-grids to scale to large areas and introduce a confidence score to model uncertainty in scene reconstruction.
  arXiv  Detail & Related papers  (2024-10-10T10:10:03Z)
• Improving classification of road surface conditions via road area extraction and contrastive learning [2.9109581496560044]
  We introduce a segmentation model to only focus the downstream classification model to the road surface in the image. Our experiments on the public RTK dataset demonstrate a significant improvement in our proposed method.
  arXiv  Detail & Related papers  (2024-07-19T15:43:16Z)
• S4C: Self-Supervised Semantic Scene Completion with Neural Fields [54.35865716337547]
  3D semantic scene understanding is a fundamental challenge in computer vision. Current methods for SSC are generally trained on 3D ground truth based on aggregated LiDAR scans. Our work presents the first self-supervised approach to SSC called S4C that does not rely on 3D ground truth data.
  arXiv  Detail & Related papers  (2023-10-11T14:19:05Z)
• Unsupervised Adaptation from Repeated Traversals for Autonomous Driving [54.59577283226982]
  Self-driving cars must generalize to the end-user's environment to operate reliably. One potential solution is to leverage unlabeled data collected from the end-users' environments. There is no reliable signal in the target domain to supervise the adaptation process. We show that this simple additional assumption is sufficient to obtain a potent signal that allows us to perform iterative self-training of 3D object detectors on the target domain.
  arXiv  Detail & Related papers  (2023-03-27T15:07:55Z)
• An Active and Contrastive Learning Framework for Fine-Grained Off-Road Semantic Segmentation [7.035838394813961]
  Off-road semantic segmentation with fine-grained labels is necessary for autonomous vehicles to understand driving scenes. Fine-grained semantic segmentation in off-road scenes usually has no unified category definition due to ambiguous nature environments. This research proposes an active and contrastive learning-based method that does not rely on pixel-wise labels.
  arXiv  Detail & Related papers  (2022-02-18T03:16:31Z)
• Model Guided Road Intersection Classification [2.9248680865344348]
  This work investigates inter-section classification from RGB images using well-consolidate neural network approaches along with a method to enhance the results based on the teacher/student training paradigm. An extensive experimental activity aimed at identifying the best input configuration and evaluating different network parameters on both the well-known KITTI dataset and the new KITTI-360 sequences shows that our method outperforms current state-of-the-art approaches on a per-frame basis and prove the effectiveness of the proposed learning scheme.
  arXiv  Detail & Related papers  (2021-04-26T09:15:28Z)
• GANav: Group-wise Attention Network for Classifying Navigable Regions in Unstructured Outdoor Environments [54.21959527308051]
  We present a new learning-based method for identifying safe and navigable regions in off-road terrains and unstructured environments from RGB images. Our approach consists of classifying groups of terrain classes based on their navigability levels using coarse-grained semantic segmentation. We show through extensive evaluations on the RUGD and RELLIS-3D datasets that our learning algorithm improves the accuracy of visual perception in off-road terrains for navigation.
  arXiv  Detail & Related papers  (2021-03-07T02:16:24Z)
• Fine-Grained Off-Road Semantic Segmentation and Mapping via Contrastive Learning [7.965964259208489]
  Road detection or traversability analysis has been a key technique for a mobile robot to traverse complex off-road scenes. understanding scenes with fine-grained labels are needed for off-road robots, as scenes are very diverse. This research proposes a contrastive learning based method to achieve meaningful scene understanding for a robot to traverse off-road.
  arXiv  Detail & Related papers  (2021-03-05T13:23:24Z)
• Low-latency Perception in Off-Road Dynamical Low Visibility Environments [0.9142067094647588]
  This work proposes a perception system for autonomous vehicles and advanced driver assistance specialized on unpaved roads and off-road environments. Almost 12,000 images of different unpaved and off-road environments were collected and labeled. We have used convolutional neural networks trained to segment obstacles areas where the car can pass through.
  arXiv  Detail & Related papers  (2020-12-23T22:54:43Z)
• VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification [116.1587709521173]
  We propose to build a large-scale vehicle dataset (called VehicleNet) by harnessing four public vehicle datasets. We design a simple yet effective two-stage progressive approach to learning more robust visual representation from VehicleNet. We achieve the state-of-art accuracy of 86.07% mAP on the private test set of AICity Challenge.
  arXiv  Detail & Related papers  (2020-04-14T05:06:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.