New submissions for Thu, 3 Feb 22

[zhuhu00]

Keyword: SLAM

A Model for Multi-View Residual Covariances based on Perspective Deformation

• Authors: Alejandro Fontan, Laura Oliva, Javier Civera, Rudolph Triebel
• Subjects: Computer Vision and Pattern Recognition (cs.CV)
• Arxiv link: https://arxiv.org/abs/2202.00765
• Pdf link: https://arxiv.org/pdf/2202.00765
• Abstract In this work, we derive a model for the covariance of the visual residuals in multi-view SfM, odometry and SLAM setups. The core of our approach is the formulation of the residual covariances as a combination of geometric and photometric noise sources. And our key novel contribution is the derivation of a term modelling how local 2D patches suffer from perspective deformation when imaging 3D surfaces around a point. Together, these add up to an efficient and general formulation which not only improves the accuracy of both feature-based and direct methods, but can also be used to estimate more accurate measures of the state entropy and hence better founded point visibility thresholds. We validate our model with synthetic and real data and integrate it into photometric and feature-based Bundle Adjustment, improving their accuracy with a negligible overhead.

  Keyword: Visual inertial

  There is no result

  Keyword: livox

  There is no result

  Keyword: loam

  There is no result

  Keyword: Visual inertial odometry

  There is no result

  Keyword: lidar

  There is no result

  Keyword: loop detection

  There is no result

  Keyword: autonomous driving

  CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous Driving

• Authors: Hao Shi, Yifan Zhou, Kailun Yang, Xiaoting Yin, Kaiwei Wang
• Subjects: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO); Image and Video Processing (eess.IV)
• Arxiv link: https://arxiv.org/abs/2202.00909
• Pdf link: https://arxiv.org/pdf/2202.00909
• Abstract Optical flow estimation is an essential task in self-driving systems, which helps autonomous vehicles perceive temporal continuity information of surrounding scenes. The calculation of all-pair correlation plays an important role in many existing state-of-the-art optical flow estimation methods. However, the reliance on local knowledge often limits the model's accuracy under complex street scenes. In this paper, we propose a new deep network architecture for optical flow estimation in autonomous driving--CSFlow, which consists of two novel modules: Cross Strip Correlation module (CSC) and Correlation Regression Initialization module (CRI). CSC utilizes a striping operation across the target image and the attended image to encode global context into correlation volumes, while maintaining high efficiency. CRI is used to maximally exploit the global context for optical flow initialization. Our method has achieved state-of-the-art accuracy on the public autonomous driving dataset KITTI-2015. Code is publicly available at https://github.com/MasterHow/CSFlow.

  Keyword: mapping

  Learning to pronounce as measuring cross lingual joint orthography-phonology complexity

• Authors: Domenic Rosati
• Subjects: Computation and Language (cs.CL)
• Arxiv link: https://arxiv.org/abs/2202.00794
• Pdf link: https://arxiv.org/pdf/2202.00794
• Abstract Recent work has demonstrated that machine learning models allow us to compare languages by showing how hard each language might be to learn under specific tasks. Following this line of investigation, we investigate what makes a language "hard to pronounce" by modelling the task of grapheme-to-phoneme (g2p) transliteration. By training a character-level transformer model on this task across 22 languages and measuring the model's proficiency against its grapheme and phoneme inventories, we show that certain characteristics emerge that separate easier and harder languages with respect to learning to pronounce. Namely that the complexity of a languages pronunciation from its orthography is due to how expressive or simple its grapheme-to-phoneme mapping is. Further discussion illustrates how future studies should consider relative data sparsity per language in order to design more fair cross lingual comparison tasks.

  Decoupled IoU Regression for Object Detection

• Authors: Yan Gao, Qimeng Wang, Xu Tang, Haochen Wang, Fei Ding, Jing Li, Yao Hu
• Subjects: Computer Vision and Pattern Recognition (cs.CV)
• Arxiv link: https://arxiv.org/abs/2202.00866
• Pdf link: https://arxiv.org/pdf/2202.00866
• Abstract Non-maximum suppression (NMS) is widely used in object detection pipelines for removing duplicated bounding boxes. The inconsistency between the confidence for NMS and the real localization confidence seriously affects detection performance. Prior works propose to predict Intersection-over-Union (IoU) between bounding boxes and corresponding ground-truths to improve NMS, while accurately predicting IoU is still a challenging problem. We argue that the complex definition of IoU and feature misalignment make it difficult to predict IoU accurately. In this paper, we propose a novel Decoupled IoU Regression (DIR) model to handle these problems. The proposed DIR decouples the traditional localization confidence metric IoU into two new metrics, Purity and Integrity. Purity reflects the proportion of the object area in the detected bounding box, and Integrity refers to the completeness of the detected object area. Separately predicting Purity and Integrity can divide the complex mapping between the bounding box and its IoU into two clearer mappings and model them independently. In addition, a simple but effective feature realignment approach is also introduced to make the IoU regressor work in a hindsight manner, which can make the target mapping more stable. The proposed DIR can be conveniently integrated with existing two-stage detectors and significantly improve their performance. Through a simple implementation of DIR with HTC, we obtain 51.3% AP on MS COCO benchmark, which outperforms previous methods and achieves state-of-the-art.

  HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection

• Authors: Ke Chen, Xingjian Du, Bilei Zhu, Zejun Ma, Taylor Berg-Kirkpatrick, Shlomo Dubnov
• Subjects: Sound (cs.SD); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS)
• Arxiv link: https://arxiv.org/abs/2202.00874
• Pdf link: https://arxiv.org/pdf/2202.00874
• Abstract Audio classification is an important task of mapping audio samples into their corresponding labels. Recently, the transformer model with self-attention mechanisms has been adopted in this field. However, existing audio transformers require large GPU memories and long training time, meanwhile relying on pretrained vision models to achieve high performance, which limits the model's scalability in audio tasks. To combat these problems, we introduce HTS-AT: an audio transformer with a hierarchical structure to reduce the model size and training time. It is further combined with a token-semantic module to map final outputs into class featuremaps, thus enabling the model for the audio event detection (i.e. localization in time). We evaluate HTS-AT on three datasets of audio classification where it achieves new state-of-the-art (SOTA) results on AudioSet and ESC-50, and equals the SOTA on Speech Command V2. It also achieves better performance in event localization than the previous CNN-based models. Moreover, HTS-AT requires only 35% model parameters and 15% training time of the previous audio transformer. These results demonstrate the high performance and high efficiency of HTS-AT.

  Keyword: localization

  LocUNet: Fast Urban Positioning Using Radio Maps and Deep Learning

• Authors: Çağkan Yapar, Ron Levie, Gitta Kutyniok, Giuseppe Caire
• Subjects: Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI); Signal Processing (eess.SP)
• Arxiv link: https://arxiv.org/abs/2202.00738
• Pdf link: https://arxiv.org/pdf/2202.00738
• Abstract This paper deals with the problem of localization in a cellular network in a dense urban scenario. Global Navigation Satellite Systems (GNSS) typically perform poorly in urban environments, where the likelihood of line-of-sight conditions is low, and thus alternative localization methods are required for good accuracy. We present LocUNet: A deep learning method for localization, based merely on Received Signal Strength (RSS) from Base Stations (BSs), which does not require any increase in computation complexity at the user devices with respect to the device standard operations, unlike methods that rely on time of arrival or angle of arrival information. In the proposed method, the user to be localized reports the RSS from BSs to a Central Processing Unit (CPU), which may be located in the cloud. Alternatively, the localization can be performed locally at the user. Using estimated pathloss radio maps of the BSs, LocUNet can localize users with state-of-the-art accuracy and enjoys high robustness to inaccuracies in the radio maps. The proposed method does not require pre-sampling of the environment; and is suitable for real-time applications, thanks to the RadioUNet, a neural network-based radio map estimator. We also introduce two datasets that allow numerical comparisons of RSS and Time of Arrival (ToA) methods in realistic urban environments.

  Ranging-Based Localizability-Constrained Deployment of Mobile Robotic Networks

• Authors: Justin Cano, Jerome Le Ny
• Subjects: Robotics (cs.RO); Multiagent Systems (cs.MA)
• Arxiv link: https://arxiv.org/abs/2202.00756
• Pdf link: https://arxiv.org/pdf/2202.00756
• Abstract In cooperative localization schemes for robotic networks relying on noisy range measurements between agents, the achievable positioning accuracy strongly depends on the network geometry. This motivates the problem of planning robot trajectories in such multi-robot systems in a way that maintains high localization accuracy. We present potential-based planning methods, where localizability potentials are introduced to characterize the quality of the network geometry for cooperative position estimation. These potentials are based on Cram\'er Rao Lower Bounds (CRLB) and provide a theoretical lower bound on the error covariance achievable by any unbiased position estimator. In the process, we establish connections between CRLBs and the theory of graph rigidity, which has been previously used to plan the motion of robotic networks. We develop decentralized deployment algorithms appropriate for large networks, and we use equality-constrained CRLBs to extend the concept of localizability to scenarios where additional information about the relative positions of the ranging sensors is known. We illustrate the resulting robot deployment methodology through simulated examples.

  Decoupled IoU Regression for Object Detection

• Authors: Yan Gao, Qimeng Wang, Xu Tang, Haochen Wang, Fei Ding, Jing Li, Yao Hu
• Subjects: Computer Vision and Pattern Recognition (cs.CV)
• Arxiv link: https://arxiv.org/abs/2202.00866
• Pdf link: https://arxiv.org/pdf/2202.00866
• Abstract Non-maximum suppression (NMS) is widely used in object detection pipelines for removing duplicated bounding boxes. The inconsistency between the confidence for NMS and the real localization confidence seriously affects detection performance. Prior works propose to predict Intersection-over-Union (IoU) between bounding boxes and corresponding ground-truths to improve NMS, while accurately predicting IoU is still a challenging problem. We argue that the complex definition of IoU and feature misalignment make it difficult to predict IoU accurately. In this paper, we propose a novel Decoupled IoU Regression (DIR) model to handle these problems. The proposed DIR decouples the traditional localization confidence metric IoU into two new metrics, Purity and Integrity. Purity reflects the proportion of the object area in the detected bounding box, and Integrity refers to the completeness of the detected object area. Separately predicting Purity and Integrity can divide the complex mapping between the bounding box and its IoU into two clearer mappings and model them independently. In addition, a simple but effective feature realignment approach is also introduced to make the IoU regressor work in a hindsight manner, which can make the target mapping more stable. The proposed DIR can be conveniently integrated with existing two-stage detectors and significantly improve their performance. Through a simple implementation of DIR with HTC, we obtain 51.3% AP on MS COCO benchmark, which outperforms previous methods and achieves state-of-the-art.

  HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection

• Authors: Ke Chen, Xingjian Du, Bilei Zhu, Zejun Ma, Taylor Berg-Kirkpatrick, Shlomo Dubnov
• Subjects: Sound (cs.SD); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS)
• Arxiv link: https://arxiv.org/abs/2202.00874
• Pdf link: https://arxiv.org/pdf/2202.00874
• Abstract Audio classification is an important task of mapping audio samples into their corresponding labels. Recently, the transformer model with self-attention mechanisms has been adopted in this field. However, existing audio transformers require large GPU memories and long training time, meanwhile relying on pretrained vision models to achieve high performance, which limits the model's scalability in audio tasks. To combat these problems, we introduce HTS-AT: an audio transformer with a hierarchical structure to reduce the model size and training time. It is further combined with a token-semantic module to map final outputs into class featuremaps, thus enabling the model for the audio event detection (i.e. localization in time). We evaluate HTS-AT on three datasets of audio classification where it achieves new state-of-the-art (SOTA) results on AudioSet and ESC-50, and equals the SOTA on Speech Command V2. It also achieves better performance in event localization than the previous CNN-based models. Moreover, HTS-AT requires only 35% model parameters and 15% training time of the previous audio transformer. These results demonstrate the high performance and high efficiency of HTS-AT.

  Automotive Parts Assessment: Applying Real-time Instance-Segmentation Models to Identify Vehicle Parts

• Authors: Syed Adnan Yusuf, Abdulmalik Ali Aldawsari, Riad Souissi
• Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
• Arxiv link: https://arxiv.org/abs/2202.00884
• Pdf link: https://arxiv.org/pdf/2202.00884
• Abstract The problem of automated car damage assessment presents a major challenge in the auto repair and damage assessment industry. The domain has several application areas ranging from car assessment companies such as car rentals and body shops to accidental damage assessment for car insurance companies. In vehicle assessment, the damage can take any form including scratches, minor and major dents to missing parts. More often, the assessment area has a significant level of noise such as dirt, grease, oil or rush that makes an accurate identification challenging. Moreover, the identification of a particular part is the first step in the repair industry to have an accurate labour and part assessment where the presence of different car models, shapes and sizes makes the task even more challenging for a machine-learning model to perform well. To address these challenges, this research explores and applies various instance segmentation methodologies to evaluate the best performing models. The scope of this work focusses on two genres of real-time instance segmentation models due to their industrial significance, namely SipMask and Yolact. These methodologies are evaluated against a previously reported car parts dataset (DSMLR) and an internally curated dataset extracted from local car repair workshops. The Yolact-based part localization and segmentation method performed well when compared to other real-time instance mechanisms with a mAP of 66.5. For the workshop repair dataset, SipMask++ reported better accuracies for object detection with a mAP of 57.0 with outcomes for AP_IoU=.50and AP_IoU=.75 reporting 72.0 and 67.0 respectively while Yolact was found to be a better performer for AP_s with 44.0 and 2.6 for object detection and segmentation categories respectively.