activity
20152026
most citedPattern-Aware Data Augmentation for LiDAR 3D Object Detection

26 citations · 155 across the 59 of their papers we have counts for

collaborators
Showing 2018 · cs.CVShow all

5 papers · 2 filters

cs.CV2018

Network Uncertainty Informed Semantic Feature Selection for Visual SLAM

Pranav Ganti, Steven L. Waslander

In order to facilitate long-term localization using a visual simultaneous localization and mapping (SLAM) algorithm, careful feature selection can help ensure that reference points…

cs.CV2018

Encoderless Gimbal Calibration of Dynamic Multi-Camera Clusters

Christopher L. Choi, Jason Rebello, Leonid Koppel +3

Dynamic Camera Clusters (DCCs) are multi-camera systems where one or more cameras are mounted on actuated mechanisms such as a gimbal. Existing methods for DCC calibration rely on…

cs.CV2018

Unlimited Road-scene Synthetic Annotation (URSA) Dataset

Matt Angus, Mohamed ElBalkini, Samin Khan +5

In training deep neural networks for semantic segmentation, the main limiting factor is the low amount of ground truth annotation data that is available in currently existing datas…

cs.CV2018

A Hierarchical Deep Architecture and Mini-Batch Selection Method For Joint Traffic Sign and Light Detection

Alex D. Pon, Oles Andrienko, Ali Harakeh +1

Traffic light and sign detectors on autonomous cars are integral for road scene perception. The literature is abundant with deep learning networks that detect either lights or sign…

cs.CV2018

In Defense of Classical Image Processing: Fast Depth Completion on the CPU

Jason Ku, Ali Harakeh, Steven L. Waslander

With the rise of data driven deep neural networks as a realization of universal function approximators, most research on computer vision problems has moved away from hand crafted c…