Data Mining Practical Machine Learning Tools and Techniques

The Visual Analysis of Human Movement

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

Self-driving vehicles are a maturing technology with the potential to reshape mobility by enhancing the safety, accessibility, efficiency, and convenience of automotive transportation. Safety-critical tasks that must be executed by a self-driving vehicle include planning of motions through a dynamic environment shared with other vehicles and pedestrians, and their robust executions via feedback control. The objective of this paper is to survey the current state of the art on planning and control algorithms with particular regard to the urban setting. A selection of proposed techniques is reviewed along with a discussion of their effectiveness. The surveyed approaches differ in the vehicle mobility model used, in assumptions on the structure of the environment, and in computational requirements. The side by side comparison presented in this survey helps to gain insight into the strengths and limitations of the reviewed approaches and assists with system level design choices.

A Survey of Motion Planning and Control Techniques for Self-Driving Urban Vehicles

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

nuScenes: A Multimodal Dataset for Autonomous Driving

The TerraMax autonomous vehicle is based on Oshkosh Truck's Medium Tactical Vehicle Replacement (MTVR) truck platform and was one of the 5 vehicles able to successfully reach the finish line of the 132 miles DARPA Grand Challenge desert race. Due to its size and the narrow passages, TerraMax had to travel slowly, but its capabilities demonstrated the maturity of the overall system. Rockwell Collins developed the autonomous intelligent Vehicle Management System (iVMS) which includes vehicle sensor management, navigation and control systems; the University of Parma provided the vehicle's vision system, while Oshkosh Truck Corp. provided project management, system integration, low level controls hardware, modeling and simulation support and the vehicle.

The TerraMax Autonomous Vehicle concludes the 2005 DARPA Grand Challenge

Describes the image processing techniques designed to localize the tracks of snowcats for the automation of transportation of goods and people during the Italian scientific missions in Antarctica. The final goal is to enable a snowcat to automatically follow the preceding one in a train-like fashion. A camera is used to acquire images of the scene; the image sequence is analyzed by a computer vision system which identifies the tracks and produces a high level description of the scene. This result is then forwarded to a further software module in charge of the control of the snowcat movement. A further optional representation, in which markers highlighting the tracks are superimposed onto the acquired image, is transmitted to a human supervisor located off board. This system has been tested in the Italian test site and was under testing in the South Pole during the early 2002 Italian scientific mission. The paper also briefly describes an alternative solution based on an evolutionary approach.

/pdf/artificial-vision-in-extreme-environments-for-snowcat-tracks-41fgg4rnzj.pdf

Artificial vision in extreme environments for snowcat tracks detection

Reliable perception of terrain slope and terrain traversability is a key-feature for any off-road unmanned ground vehicle, as well as for any Driver Assistance Systems designed to work in extreme environments, like mining. In this paper we want to present an innovative technique to build a 3D elevation map of the traversable terrain from a world's 3D dense data set, in real time. The 3D points are grouped into lateral and longitudinal equally spaced slices, then they are projected onto the corresponding slices' reference planes. The projections are then analyzed by a biologically inspired Optimization Algorithm able to segment points into terrains inlier and outlier; the resulting 2D terrain slopes represent an optimal terrain approximation along each slice. Finally, the 2D approximations are merged together, to create the overall 3D terrain surface. The algorithm has been successfully tested with 3D data provided by a stereo camera system mounted on a Cat® wheel loader operating in a mining environment.

/pdf/real-time-3d-terrain-elevation-mapping-using-ants-134ip5pcam.pdf

Real time 3D terrain elevation mapping using ants Optimization Algorithm and stereo vision

This paper presents a monocular night vision system specifically developed for detecting very distant pedestrians. The focus of the system is the recognition of pedestrians that are between 40 and 100 m away from the camera. The system is intended to integrate with an existing system, which is capable of detecting pedestrians at distances less than 40 m. At very large distances, pedestrians appear at low resolution, and this requires a specific detection algorithm, rather than an adaptation of an existing one. The presented system performs best in rural environments, where it can locate pedestrians at such great distances, that the pedestrians are hardly visible even to a human driver.

/pdf/a-night-vision-module-for-the-detection-of-distant-2ukqczux5u.pdf

Alberto Broggi

Papers

The TerraMax Autonomous Vehicle concludes the 2005 DARPA Grand Challenge

Artificial vision in extreme environments for snowcat tracks detection

Real time 3D terrain elevation mapping using ants Optimization Algorithm and stereo vision

A Night Vision Module for the Detection of Distant Pedestrians

VIAC Expedition Toward Autonomous Mobility [From the Field]