Shulou(Shulou.com)06/03 Report--

OpenCV

OpenCV is a cross-platform computer vision library released under the BSD license (open source) that can run on Linux, Windows, Android, and Mac OS operating systems. It is lightweight and efficient-it consists of a series of C functions and a small number of C++ classes, provides interfaces to Python, Ruby, MATLAB and other languages, and implements many general algorithms in image processing and computer vision.

OpenCV is written in C++ language, and its main interface is C++ language, but it still retains a large number of C language interfaces. The library also has a large number of Python, Java and MATLAB/OCTAVE (version 2.5) interfaces. The API interface functions for these languages are available through online documentation. Support for C#, Ch, and Ruby,GO is also available today.

ViCANdo

ViCANdo Suite is a development and testing platform for intelligent driving functions, which can synchronously collect all kinds of data needed. At the same time, the tools are integrated with OpenCV. Engineers can directly use the relevant functions of OpenCV to develop.

ViCANdo has an open SDK that allows for the creation of custom interfaces and allows algorithms under development to be used as part of the ViCANdo itself to execute at very high performance. By using the Matlab/Simulink extension in ViCANSim, or by using the built-in simulation engine for network simulation or video algorithm development.

Data sources directly supported by ViCANdo Suite

Example application:

Real-time lane recognition and real-time display in ViCANdo, through the direct integration of lane recognition algorithm in ViCANdo, convenient and intuitive display of lane recognition algorithm, and using the extended function of ViCANdo to overlay the identified lane, heading and other information with video display, it is convenient to debug the algorithm.

In the project above, we add one camera to collect the road information, and at the same time collect the vehicle information with two CAN channels, extract the lane information through the image, and display the identified lane information and the vehicle route information on the image in real time combined with the vehicle status information.

Example application:

Look around the camera stitching and real-time display, first of all, through the ViCANdo support for LVDS cameras, you can directly access the video data of general vehicle cameras to the platform, for the development engineers do not need to invest in unnecessary driver development and other work, directly integrate the OpenCV-based video stitching algorithm in ViCANdo, and directly display the stitching results in the ViCANdo interface.

In the project above, we collect the video information of the four-way vehicle camera in real time through the LVDS board (not the rear-mounted camera, which can ensure that the parameters of the algorithm are the parameters of the original car camera), load the image stitching algorithm in the software, display it directly in the software window, and display the original image of the fisheye camera at the same time.

ViCANdo Suite product introduction

ViCANdo Suite is a software suite for the development and testing of intelligent driving functions.

The software contains the following components:

ViCANdo:

ViCANdo is a cross-platform data recording and analysis tool developed for AD/ADAS, which supports operating systems such as Windows, Linux, MacOS, X86, ARM and other platforms.

ViCANlog:

The software designed for vehicle-end road test acquisition can run on any linux-based hardware equipment and collect data unattended. In addition to general computers, it also supports Nvidia TX-2, Xavier,Nexcom and other devices.

ViCANdroid:

APP on Android can collect CAN bus, video, audio, GPS and other data, built-in FTP service, and can automatically upload data to the server. It is convenient to process and analyze the data.

ViCANsim:

Through the integration with OpenCV and Matlab/Simulink ™, it is convenient for users to deploy their own algorithms on ViCANsim, which also has an interface with Matlab/Simulink ™.

ViCANbedded:

The goal of ViCANbedded is to be used in an embedded environment, the same as ViCANdo. It is designed to easily migrate the source code from the PC platform to the embedded environment. Currently, it supports QTEmbedded 4.X and later, QNX, Velocity, VxWorks, and so on.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.