Multiview RGB-D Dataset for Object Instance Detection

By Georgios Georgakis, Md. Alimoor Reza, Arsalan Mousavian, Phi Hung Le, Jana Kosecka. 2016

90 citations recorded by the source corpus.

This paper presents a new multi-view RGB-D dataset of nine kitchen scenes, each containing several objects in realistic cluttered environments including a subset of objects from the BigBird dataset. The viewpoints of the scenes are densely sampled and objects in the scenes are annotated with bounding boxes and in the 3D point cloud. Also, an approach for detection and recognition is presented, which is comprised of two parts: (i) a new multi-view 3D proposal generation method and (ii) the development of several recognition baselines using AlexNet to score our proposals, which is trained either on crops of the dataset or on synthetically composited training images. Finally, we compare the performance of the object proposals and a detection baseline to the Washington RGB-D Scenes (WRGB-D) dataset and demonstrate that our Kitchen scenes dataset is more challenging for object detection and recognition. The dataset is available at: http://cs.gmu.edu/~robot/gmu-kitchens.html.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

Citations in the corpus

Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021, background): “nition [23, 85, 126, 155] to deal with video (frequent FoV changes, objects entering/exiting the view) and to reason about objects in the context of a 3D environment.”
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation (2020, methodology): “(4) We benchmark and thoroughly study Copy-Paste on the widely used COCO and LVIS datasets while Cut-Paste-and-Learn uses the GMU dataset [16].”
Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection (2017, methodology): “Three dataset splits with 6 scenes for training and 3 for testing have been provided in [13] to conduct experiments on the GMU Kitchen dataset.”
Continual Universal Object Detection (2020, unknown): “KITTI [8] and Kitchen [9] have disjoint categories and signiﬁcant domain discrepancies; can we learn those sequentially without forgetting?”
SEGCloud: Semantic Segmentation of 3D Point Clouds (2017, background): “Several 3D Scene datasets have been made available to the research community [56, 4, 5, 31, 59, 72, 52, 16, 24, 74].”
A dataset for developing and benchmarking active vision (2017, background): “Scene dataset, [2], [17],[1], and [18] do explore environments more than “table-top” data but do not have a dense set of views to simulate robot motion.”
Towards Universal Object Detection by Domain Attention (2019, methodology): “To train and evaluate universal/multi-domain object detection systems, we established a new universal object de- tection benchmark (UODB) of 11 datasets: Pascal VOC [6], WiderFace [58], KITTI [9], LISA [33], DOTA [53], COCO [27], Watercolor [17], Clipart [17], Comic [17], Kitchen [10] and DeepLesion”
Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism (2022, unknown): “Following the continual object detection settings in [34] and [23], we conduct experiments on COCO [30], Pascal VOC [11], KITTI [14] and Kitchen [15].”
Multi-task incremental learning for object detection (2020, methodology): “KITTI [10] and Kitchen [11] have disjoint categories and signiﬁcant domain discrepancies; can we learn those sequentially without forgetting?”