685 papers with code • 4 benchmarks • 59 datasets
Autonomous driving is the task of driving a vehicle without human conduction.
While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving.
SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving
In addition to requiring high accuracy to ensure safety, object detection for autonomous driving also requires real-time inference speed to guarantee prompt vehicle control, as well as small model size and energy efficiency to enable embedded system deployment.
In the case of traffic line detection, an essential perception module, many condition should be considered, such as number of traffic lines and computing power of the target system.
This eliminates the need for human engineers to anticipate what is important in an image and foresee all the necessary rules for safe driving.
We evaluate the model using a calibration dataset with several different lenses and compare the models using the metrics that are relevant for Visual Odometry, i. e., reprojection error, as well as computation time for projection and unprojection functions and their Jacobians.
In an effort to help align the research community's contributions with real-world self-driving problems, we introduce a new large scale, high quality, diverse dataset.
To our knowledge, this is the first successful case of driving policy trained by reinforcement learning that can adapt to real world driving data.