Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Ammirato, Phil"'
Autor:
Ammirato, Phil, Berg, Alexander C.
The Probabilistic Object Detection Challenge evaluates object detection methods using a new evaluation measure, Probability-based Detection Quality (PDQ), on a new synthetic image dataset. We present our submission to the challenge, a fine-tuned vers
Externí odkaz:
http://arxiv.org/abs/1908.03621
While state-of-the-art general object detectors are getting better and better, there are not many systems specifically designed to take advantage of the instance detection problem. For many applications, such as household robotics, a system may need
Externí odkaz:
http://arxiv.org/abs/1803.04610
We present a new public dataset with a focus on simulating robotic vision tasks in everyday indoor environments using real imagery. The dataset includes 20,000+ RGB-D images and 50,000+ 2D bounding boxes of object instances densely captured in 9 uniq
Externí odkaz:
http://arxiv.org/abs/1702.08272
Autor:
Poirson, Patrick, Ammirato, Phil, Fu, Cheng-Yang, Liu, Wei, Kosecka, Jana, Berg, Alexander C.
For applications in navigation and robotics, estimating the 3D pose of objects is as important as detection. Many approaches to pose estimation rely on detecting or tracking parts or keypoints [11, 21]. In this paper we build on a recent state-of-the
Externí odkaz:
http://arxiv.org/abs/1609.05590