A
Adam Herout
Researcher at Brno University of Technology
Publications - 116
Citations - 2178
Adam Herout is an academic researcher from Brno University of Technology. The author has contributed to research in topics: Hough transform & Object detection. The author has an hindex of 24, co-authored 112 publications receiving 1706 citations.
Papers
More filters
Proceedings ArticleDOI
BoxCars: 3D Boxes as CNN Input for Improved Fine-Grained Vehicle Recognition
TL;DR: This work is showing that extracting additional data from the video stream and feeding it into the deep convolutional neural network boosts the recognition performance considerably, and can considerably improve the performance of traffic surveillance systems.
Proceedings ArticleDOI
Vehicle Re-identification for Automatic Video Traffic Surveillance
Dominik Zapletal,Adam Herout +1 more
TL;DR: The proposed method works with a high accuracy and in 85 milliseconds of the CPU (Core i7) computation time per one vehicle re-identification assuming the fullHD resolution video input.
Journal ArticleDOI
BoxCars: Improving Fine-Grained Recognition of Vehicles Using 3-D Bounding Boxes in Traffic Surveillance
TL;DR: The proposed method significantly improves CNN classification accuracy and outperforms the state-of-the-art methods for fine-grained recognition.
Calibration of RGB camera with velodyne LiDAR
TL;DR: This paper presents a novel 3D marker for coarse calibration which can be robustly detected in both the camera image and the LiDAR scan and requires only a single pair of camera-LiDAR frames for estimating large sensors displacement.
Proceedings ArticleDOI
Automatic Camera Calibration for Traffic Understanding.
TL;DR: This work proposes a method for fully automatic calibration of traffic surveillance cameras for targeted applications, which allows for calibration of the camera – including scale – without any user input, only from several minutes of input surveillance video.