“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, tracking and segmentation of agents in the environment. Most autonomous vehicles, however, carry a combination of cameras and range sensors such as lidar and radar. As machine learning based methods for detection and tracking become more prevalent, there is a need to train and evaluate such methods on datasets containing range sensor data along with images. In this work we present nuTonomy scenes (nuScenes), the first dataset to carry the full autonomous vehicle sensor suite: 6 cameras, 5 radars and 1 lidar, all with full 360 degree field of view. nuScenes comprises 1000 scenes, each 20s long and fully annotated with 3D bounding boxes for 23 classes and 8 attributes. It has 7x as many annotations and 100x as many images as the pioneering KITTI dataset. We define novel 3D detection and tracking metrics. We also provide careful dataset analysis as well as baselines for lidar and image based detection and tracking. Data, development kit and more information are available online.

nuScenes: A multimodal dataset for autonomous driving

Обнаружение транспортных средств на изображениях загородных шоссе на основе метода Single shot multibox Detector

/pdf/nuscenes-a-multimodal-dataset-for-autonomous-driving-3znmpkqyuu.pdf

nuScenes: A Multimodal Dataset for Autonomous Driving

Automated driving systems (ADSs) promise a safe, comfortable and efficient driving experience. However, fatalities involving vehicles equipped with ADSs are on the rise. The full potential of ADSs cannot be realized unless the robustness of state-of-the-art is improved further. This paper discusses unsolved problems and surveys the technical aspect of automated driving. Studies regarding present challenges, high-level system architectures, emerging methodologies and core functions including localization, mapping, perception, planning, and human machine interfaces, were thoroughly reviewed. Furthermore, many state-of-the-art algorithms were implemented and compared on our own platform in a real-world driving setting. The paper concludes with an overview of available datasets and tools for ADS development.

A Survey of Autonomous Driving: Common Practices and Emerging Technologies

Social distancing (SD) is an effective measure to prevent the spread of the infectious Coronavirus Disease 2019 (COVID-19). However, a lack of spatial awareness may cause unintentional violations of this new measure. Against this backdrop, we propose an active surveillance system to slow the spread of COVID-19 by warning individuals in a region-of-interest. Our contribution is twofold. First, we introduce a vision-based real-time system that can detect SD violations and send non-intrusive audio-visual cues using state-of-the-art deep-learning models. Second, we define a novel critical social density value and show that the chance of SD violation occurrence can be held near zero if the pedestrian density is kept under this value. The proposed system is also ethically fair: it does not record data nor target individuals, and no human supervisor is present during the operation. The proposed system was evaluated across real-world datasets.

/pdf/a-vision-based-social-distancing-and-critical-density-369zydivcu.pdf

A Vision-Based Social Distancing and Critical Density Detection System for COVID-19.

Social distancing has been proven as an effective measure against the spread of the infectious COronaVIrus Disease 2019 (COVID-19). However, individuals are not used to tracking the required 6-feet (2-meters) distance between themselves and their surroundings. An active surveillance system capable of detecting distances between individuals and warning them can slow down the spread of the deadly disease. Furthermore, measuring social density in a region of interest (ROI) and modulating inflow can decrease social distancing violation occurrence chance. 
On the other hand, recording data and labeling individuals who do not follow the measures will breach individuals' rights in free-societies. Here we propose an Artificial Intelligence (AI) based real-time social distancing detection and warning system considering four important ethical factors: (1) the system should never record/cache data, (2) the warnings should not target the individuals, (3) no human supervisor should be in the detection/warning loop, and (4) the code should be open-source and accessible to the public. Against this backdrop, we propose using a monocular camera and deep learning-based real-time object detectors to measure social distancing. If a violation is detected, a non-intrusive audio-visual warning signal is emitted without targeting the individual who breached the social distancing measure. Also, if the social density is over a critical value, the system sends a control signal to modulate inflow into the ROI. We tested the proposed method across real-world datasets to measure its generality and performance. The proposed method is ready for deployment, and our code is open-sourced.

A Vision-based Social Distancing and Critical Density Detection System for COVID-19

A novel method for integrating driving behavior and traffic context through signal symbolization is presented in this paper. This symbolization framework is proposed as a data reduction method for naturalistic driving studies. Continuous sensor signals have been converted and reduced into sequences of symbols (chunks) using a sticky hierarchical Dirichlet process hidden Markov model and a nested Pitman–Yor language model. Then, co-occurrence chunking (COOC), the proposed integration method, has been applied to the driver behavior and the traffic context chunks. After the integration, COOC chunks have been associated with prototype driving scenes by using latent Dirichlet allocation. Finally, the translated sequence of chunks has been clustered into groups. Risky lane change detection experiments have been conducted with the symbolized data for evaluation purposes. A dataset comprised of 988 lane change scenes has been utilized for this process. Co-occurrence chunking with clustering provided the best risky lane change detection.

Integrating Driving Behavior and Traffic Context Through Signal Symbolization for Data Reduction and Risky Lane Change Detection

Advanced driver assistance and automated driving systems rely on risk estimation modules to predict and avoid dangerous situations. Current methods use expensive sensor setups and complex processing pipelines, limiting their availability and robustness. To address these issues, we introduce a novel deep learning based driving risk assessment framework for classifying dangerous lane change behavior in short video clips captured by a monocular camera. First, semantic segmentation masks were generated from individual video frames with a pre-trained Mask R-CNN model. Then, frames overlayed with these masks were fed into a time distributed CNN-LSTM network with a final softmax classification layer. This network was trained on a semi-naturalistic lane change dataset with annotated risk labels. A comprehensive comparison of state-of-the-art pre-trained feature extractors was carried out to find the best network layout and training strategy. The best result, with a 0.937 AUC score, was obtained with the proposed framework. Our code and trained models are available open-source1.

Ekim Yurtsever

Papers

A Survey of Autonomous Driving: Common Practices and Emerging Technologies

A Vision-Based Social Distancing and Critical Density Detection System for COVID-19.

A Vision-based Social Distancing and Critical Density Detection System for COVID-19

Integrating Driving Behavior and Traffic Context Through Signal Symbolization for Data Reduction and Risky Lane Change Detection

Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmentation Mask Transfer