Investigating the Importance of Shape Features, Color Constancy, Color Spaces and Similarity Measures in Open-Ended 3D Object Recognition

• URL: http://arxiv.org/abs/2002.03779v2
• Date: Sat, 26 Sep 2020 12:18:24 GMT
• Title: Investigating the Importance of Shape Features, Color Constancy, Color Spaces and Similarity Measures in Open-Ended 3D Object Recognition
• Authors: S. Hamidreza Kasaei, Maryam Ghorbani, Jits Schilperoort, Wessel van der Rest
• Abstract summary: We study the importance of shape information, color constancy, color spaces, and various similarity measures in open-ended 3D object recognition. Experimental results show that all of the textitcombinations of color and shape yields significant improvements over the textitshape-only and textitcolor-only approaches.
• Score: 4.437005770487858
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the recent success of state-of-the-art 3D object recognition approaches, service robots are frequently failed to recognize many objects in real human-centric environments. For these robots, object recognition is a challenging task due to the high demand for accurate and real-time response under changing and unpredictable environmental conditions. Most of the recent approaches use either the shape information only and ignore the role of color information or vice versa. Furthermore, they mainly utilize the $L_n$ Minkowski family functions to measure the similarity of two object views, while there are various distance measures that are applicable to compare two object views. In this paper, we explore the importance of shape information, color constancy, color spaces, and various similarity measures in open-ended 3D object recognition. Towards this goal, we extensively evaluate the performance of object recognition approaches in three different configurations, including \textit{color-only}, \textit{shape-only}, and \textit{ combinations of color and shape}, in both offline and online settings. Experimental results concerning scalability, memory usage, and object recognition performance show that all of the \textit{combinations of color and shape} yields significant improvements over the \textit{shape-only} and \textit{color-only} approaches. The underlying reason is that color information is an important feature to distinguish objects that have very similar geometric properties with different colors and vice versa. Moreover, by combining color and shape information, we demonstrate that the robot can learn new object categories from very few training examples in a real-world setting.

Related papers

• THOR2: Leveraging Topological Soft Clustering of Color Space for Human-Inspired Object Recognition in Unseen Environments [1.9950682531209158]
  This study presents a 3D shape and color-based descriptor, TOPS2, for point clouds generated from RGB-D images and an accompanying recognition framework, THOR2. The TOPS2 descriptor embodies object unity, a human cognition mechanism, by retaining the slicing-based topological representation of 3D shape from the TOPS descriptor. THOR2, trained using synthetic data, demonstrates markedly improved recognition accuracy compared to THOR, its 3D shape-based predecessor.
  arXiv  Detail & Related papers  (2024-08-02T21:24:14Z)
• Learning-based Relational Object Matching Across Views [63.63338392484501]
  We propose a learning-based approach which combines local keypoints with novel object-level features for matching object detections between RGB images. We train our object-level matching features based on appearance and inter-frame and cross-frame spatial relations between objects in an associative graph neural network.
  arXiv  Detail & Related papers  (2023-05-03T19:36:51Z)
• ColorSense: A Study on Color Vision in Machine Visual Recognition [57.916512479603064]
  We collect 110,000 non-trivial human annotations of foreground and background color labels from visual recognition benchmarks. We validate the use of our datasets by demonstrating that the level of color discrimination has a dominating effect on the performance of machine perception models. Our findings suggest that object recognition tasks such as classification and localization are susceptible to color vision bias.
  arXiv  Detail & Related papers  (2022-12-16T18:51:41Z)
• Lifelong Ensemble Learning based on Multiple Representations for Few-Shot Object Recognition [6.282068591820947]
  We present a lifelong ensemble learning approach based on multiple representations to address the few-shot object recognition problem. To facilitate lifelong learning, each approach is equipped with a memory unit for storing and retrieving object information instantly. We have performed extensive sets of experiments to assess the performance of the proposed approach in offline, and open-ended scenarios.
  arXiv  Detail & Related papers  (2022-05-04T10:29:10Z)
• Contrastive Object Detection Using Knowledge Graph Embeddings [72.17159795485915]
  We compare the error statistics of the class embeddings learned from a one-hot approach with semantically structured embeddings from natural language processing or knowledge graphs. We propose a knowledge-embedded design for keypoint-based and transformer-based object detection architectures.
  arXiv  Detail & Related papers  (2021-12-21T17:10:21Z)
• ObjectFolder: A Dataset of Objects with Implicit Visual, Auditory, and Tactile Representations [52.226947570070784]
  We present Object, a dataset of 100 objects that addresses both challenges with two key innovations. First, Object encodes the visual, auditory, and tactile sensory data for all objects, enabling a number of multisensory object recognition tasks. Second, Object employs a uniform, object-centric simulations, and implicit representation for each object's visual textures, tactile readings, and tactile readings, making the dataset flexible to use and easy to share.
  arXiv  Detail & Related papers  (2021-09-16T14:00:59Z)
• Simultaneous Multi-View Object Recognition and Grasping in Open-Ended Domains [0.0]
  We propose a deep learning architecture with augmented memory capacities to handle open-ended object recognition and grasping simultaneously. We demonstrate the ability of our approach to grasp never-seen-before objects and to rapidly learn new object categories using very few examples on-site in both simulation and real-world settings.
  arXiv  Detail & Related papers  (2021-06-03T14:12:11Z)
• Open-Ended Fine-Grained 3D Object Categorization by Combining Shape and Texture Features in Multiple Colorspaces [5.89118432388542]
  In this work, shape information encodes the common patterns of all categories, while texture information is used to describe the appearance of each instance in detail. The proposed network architecture out-performed the selected state-of-the-art approaches in terms of object classification accuracy and scalability.
  arXiv  Detail & Related papers  (2020-09-19T14:06:18Z)
• Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve [54.054575408582565]
  We propose to leverage existing large-scale datasets of 3D models to understand the underlying 3D structure of objects seen in an image. We present Mask2CAD, which jointly detects objects in real-world images and for each detected object, optimize for the most similar CAD model and its pose. This produces a clean, lightweight representation of the objects in an image.
  arXiv  Detail & Related papers  (2020-07-26T00:08:37Z)
• Instance-aware Image Colorization [51.12040118366072]
  In this paper, we propose a method for achieving instance-aware colorization. Our network architecture leverages an off-the-shelf object detector to obtain cropped object images. We use a similar network to extract the full-image features and apply a fusion module to predict the final colors.
  arXiv  Detail & Related papers  (2020-05-21T17:59:23Z)
• Variable-Viewpoint Representations for 3D Object Recognition [27.913222855275997]
  We show that two types of input representations exist at two extremes of a common representational continuum. We identify interesting intermediate representations that lie at points in between these two extremes. We show, through systematic empirical experiments, how accuracy varies along this continuum as a function of input information.
  arXiv  Detail & Related papers  (2020-02-08T10:06:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.