Ego-Object Discovery

2015-04-07 · Marc Bolaños, Petia Radeva

Lifelogging devices are spreading faster everyday. This growth can represent great benefits to develop methods for extraction of meaningful information about the user wearing the device and his/her environment. In this paper, we propose a semi-supervised strategy for easily discovering objects relevant to the person wearing a first-person camera. Given an egocentric video/images sequence acquired by the camera, our algorithm uses both the appearance extracted by means of a convolutional neural network and an object refill methodology that allows to discover objects even in case of small amount of object appearance in the collection of images. An SVM filtering strategy is applied to deal with the great part of the False Positive object candidates found by most of the state of the art object detectors. We validate our method on a new egocentric dataset of 4912 daily images acquired by 4 persons as well as on both PASCAL 2012 and MSRC datasets. We obtain for all of them results that largely outperform the state of the art approach. We make public both the EDUB dataset and the algorithm code.

📄 PDF Abstract BibTeX arXiv:1504.01639

Code (1)

MarcBS/Ego-Object_Discovery 공식 구현

Tasks

ObjectObject Discovery

Methods 이 논문이 사용한 방법론

SVM A Support Vector Machine, or SVM, is a non-parametric supervised learning model. For non-linear classification and regression, they utilise the kernel trick to map inputs…

Large-Scale Object Mining for Object Discovery from Unlabeled Video

2019-02-28 · Aljosa Osep, Paul Voigtlaender, Jonathon Luiten, Stefan Breuers 외

This paper addresses the problem of object discovery from unlabeled driving videos captured in a realistic automotive setting. Identifying recurring object categories in such raw video streams is a very challenging probl…

Clustering Object Object Discovery

The Background Also Matters: Background-Aware Motion-Guided Objects Discovery

2023-11-05 · Sandra Kara, Hejer Ammar, Florian Chabot, Quoc-Cuong Pham

Recent works have shown that objects discovery can largely benefit from the inherent motion information in video data. However, these methods lack a proper background processing, resulting in an over-segmentation of the …

Object Object Discovery Optical Flow Estimation

Object Discovery in Videos as Foreground Motion Clustering

2018-12-06 · CVPR 2019 6 · Christopher Xie, Yu Xiang, Zaid Harchaoui, Dieter Fox

We consider the problem of providing dense segmentation masks for object discovery in videos. We formulate the object discovery problem as foreground motion clustering, where the goal is to cluster foreground pixels in v…

Clustering Motion Segmentation Object Object Discovery+2

Simultaneous Localization, Mapping, and Manipulation for Unsupervised Object Discovery

2014-11-04 · Lu Ma, Mahsa Ghafarianzadeh, Dave Coleman, Nikolaus Correll 외

We present an unsupervised framework for simultaneous appearance-based object discovery, detection, tracking and reconstruction using RGBD cameras and a robot manipulator. The system performs dense 3D simultaneous locali…

Motion Segmentation Object Object Discovery Simultaneous Localization and Mapping

Image Segmentation-based Unsupervised Multiple Objects Discovery

2022-12-20 · Sandra Kara, Hejer Ammar, Florian Chabot, Quoc-Cuong Pham

Unsupervised object discovery aims to localize objects in images, while removing the dependence on annotations required by most deep learning-based methods. To address this problem, we propose a fully unsupervised, botto…

Class-agnostic Object Detection Image Segmentation Object object-detection+4