The motion of the camera can cause images of pedestrians to be captured at extreme angles. This can lead to very poor pedestrian detection performance when using standard pedestrian detectors. To address this issue, we propose a Rotational Rectification Network (R2N) that can be inserted into any CNN-based pedestrian (or object) detector to adapt it to significant changes in camera rotation.
This paper describes computer vision techniques for early-season measurement of vine canopy parameters; leaf count, leaf area and shoot count.
本文档是卡耐基梅隆大学机器人研究所的技术论文。
Keywords: Reinforcement Learning, Robotic Manipulation, Automatic Curriculum
Generation
本文档是卡耐基梅隆大学机器人研究所的技术论文。
Deploying a system that probes the subsurface brings its own challenges and to that end, we designed, built and field tested an autonomous robot that can collect subsurface samples using a 1m drill.
This paper describes the robot and science instruments and lessons from designing and operating such a system.
Our method yields R-squared correlation of 0.88 for stalk count and a mean absolute error of
2.77mm where average stalk width is 14.354mm. Our approach is 30 times faster for stalk count and 270 times faster for stalk width measurement.
本文档是卡耐基梅隆大学机器人研究所的技术论文。
Looking Forward: A Semantic Mapping System for Scouting with Micro-Aerial Vehicles
Our ultimate goal is to enable MAVs to perform autonomous scouting. In this paper, we describe a semantic mapping system designed to support this goal. The system maintains a 2.5D map describing its belief about the location of semantic classes of interest, using forward-looking cameras and state estimation.
Recognizing Visual Signatures of Spontaneous Head Gestures
We propose a novel Multi-Scale Deep Convolution-LSTM architecture, capable of recognizing short and long term motion patterns found in head gestures, from video data of natural and unconstrained conversations.
本文档是卡耐基梅隆大学机器人研究所的技术论文。
工业4.0创新平台 版权所有 All Rights Reserved, Copyright© 2013- 京ICP备14017844号-3
