JunshengFu/vehicle-detection: Created vehicle detection pipeline with two approaches: (1) deep neural networks (YOLO framework) and (2) support vector machines ( OpenCV + HOG).


A demo of Vehicle Detection System: a monocular camera is used for detecting vehicles.

(1) Highway Drive (with Lane Departure Warning) (Click to see the full video)


(2) City Drive (Vehicle Detection only) (Click to see the full video)


Code & Files

1. My project includes the following files

Others are the same as in the repository of Lane Departure Warning System:

  • contains the script to calibrate camera and save the calibration results
  • contains the lane class
  • examples folder contains the sample images and videos

2. Dependencies & my environment

Anaconda is used for managing my dependencies.

  • You can use provided environment-gpu.yml to install the dependencies.
  • OpenCV3, Python3.5, tensorflow, CUDA8
  • OS: Ubuntu 16.04

3. How to run the code

(1) Download weights for YOLO

You can download the weight from here and save it to
the weights folder.

(2) If you want to run the demo,

Read More

Coronavirus bill would provide $114 billion to prop up faltering transportation networks

As states have expanded orders and advice to people to remain at home in an effort to slow the spread of the virus, the numbers of people traveling and buying tickets for planes and trains has slowed to a trickle. On Tuesday, the Transportation Security Administration reported a nearly 90 percent decline in passenger numbers compared to last year. Transit agencies across the country have described similar drop-offs in demand.

The provisions in the congressional deal are designed to ensure that businesses don’t go bankrupt or public agencies default on their debts before passenger numbers recover.

Some details in the $2 trillion legislation were still being finalized, but in a presentation Wednesday afternoon, Jeff Davis, a senior fellow at the Eno Center for Transportation, said he did not expect any changes to affect the final figures for transportation.

The bill is expected to pass the Senate on Wednesday before heading

Read More

bstabler/TransportationNetworks: Transportation Networks for Research

Transportation Networks is a networks repository for transportation research.

If you are developing algorithms in this field, you probably asked yourself
more than once: where can I get good data? The purpose of this site is to
provide an answer for this question! This site currently contains several examples
for the traffic assignment problem. Suggestions and additional data are always welcome.

Many of these networks are for studying the Traffic Assignment Problem, which is one of the most
basic problems in transportation research. Theoretical background can be found in
“The Traffic Assignment Problem – Models and Methods” by Michael Patriksson, VSP 1994,
as well as in many other references.

This repository is an update to Dr. Hillel Bar-Gera’s TNTP.
As of May 1, 2016, data updates will be made only here, and not in the original website.

Each individual network and related files is stored in a separate folder. There

Read More