P
Philip Lenz
Researcher at Karlsruhe Institute of Technology
Publications - 11
Citations - 18857
Philip Lenz is an academic researcher from Karlsruhe Institute of Technology. The author has contributed to research in topics: Optical flow & Object detection. The author has an hindex of 8, co-authored 11 publications receiving 12589 citations.
Papers
More filters
Proceedings ArticleDOI
Are we ready for autonomous driving? The KITTI vision benchmark suite
TL;DR: The autonomous driving platform is used to develop novel challenging benchmarks for the tasks of stereo, optical flow, visual odometry/SLAM and 3D object detection, revealing that methods ranking high on established datasets such as Middlebury perform below average when being moved outside the laboratory to the real world.
Journal ArticleDOI
Vision meets robotics: The KITTI dataset
TL;DR: A novel dataset captured from a VW station wagon for use in mobile robotics and autonomous driving research, using a variety of sensor modalities such as high-resolution color and grayscale stereo cameras and a high-precision GPS/IMU inertial navigation system.
Proceedings ArticleDOI
Sparse scene flow segmentation for moving object detection in urban environments
TL;DR: This paper presents an approach for object detection utilizing sparse scene flow, which does not rely on object classes and allows for a robust detection of dynamic objects in traffic scenes.
Proceedings ArticleDOI
FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computation
TL;DR: In this article, a dynamic version of the successive shortest-path algorithm is introduced to solve the data association problem optimally while reusing computation, resulting in faster inference than standard solvers.
Posted Content
FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computation
TL;DR: This paper introduces a dynamic version of the successive shortest-path algorithm which solves the data association problem optimally while reusing computation, resulting in faster inference than standard solvers and an approximate online solution with bounded memory and computation which is capable of handling videos of arbitrary length while performing tracking in real time.