Liefeng Bo

A large-scale hierarchical multi-view RGB-D object dataset

Over the last decade, the availability of public image repositories and recognition benchmarks has enabled rapid progress in visual object category and instance detection. Today we are witnessing the birth of a new generation of sensing technologies capable of providing high quality synchronized videos of both color and depth, the RGB-D (Kinect-style) camera. With its advanced sensing capabilities and the potential for mass adoption, this technology represents an opportunity to dramatically increase robotic object recognition, manipulation, navigation, and interaction capabilities. In this paper, we introduce a large-scale, hierarchical multi-view object dataset collected using an RGB-D camera. The dataset contains 300 objects organized into 51 categories and has been made publicly available to the research community so as to enable rapid progress based on this promising technology. This paper describes the dataset collection procedure and introduces techniques for RGB-D based object recognition and detection, demonstrating that combining color and depth information substantially improves quality of results.

Multiobjective immune algorithm with nondominated neighbor-based selection

Nondominated Neighbor Immune Algorithm (NNIA) is proposed for multiobjective optimization by using a novel nondominated neighbor-based selection technique, an immune inspired operator, two heuristic search operators, and elitism. The unique selection technique of NNIA only selects minority isolated nondominated individuals in the population. The selected individuals are then cloned proportionally to their crowding-distance values before heuristic search. By using the nondominated neighbor-based selection and proportional cloning, NNIA pays more attention to the less-crowded regions of the current trade-off front. We compare NNIA with NSGA-II, SPEA2, PESA-II, and MISA in solving five DTLZ problems, five ZDT problems, and three low-dimensional problems. The statistical analysis based on three performance metrics including the coverage of two sets, the convergence metric, and the spacing, show that the unique selection method is effective, and NNIA is an effective algorithm for solving multiobjective optimization problems. The empirical study on NNIAs scalability with respect to the number of objectives shows that the new algorithm scales well along the number of objectives.

RGB-(D) scene labeling: Features and algorithms

Scene labeling research has mostly focused on outdoor scenes, leaving the harder case of indoor scenes poorly understood. Microsoft Kinect dramatically changed the landscape, showing great potentials for RGB-D perception (color+depth). Our main objective is to empirically understand the promises and challenges of scene labeling with RGB-D. We use the NYU Depth Dataset as collected and analyzed by Silberman and Fergus [30]. For RGB-D features, we adapt the framework of kernel descriptors that converts local similarities (kernels) to patch descriptors. For contextual modeling, we combine two lines of approaches, one using a superpixel MRF, and the other using a segmentation tree. We find that (1) kernel descriptors are very effective in capturing appearance (RGB) and shape (D) similarities; (2) both superpixel MRF and segmentation tree are useful in modeling context; and (3) the key to labeling accuracy is the ability to efficiently train and test with large-scale data. We improve labeling accuracy on the NYU Dataset from 56.6% to 76.1%. We also apply our approach to image-only scene labeling and improve the accuracy on the Stanford Background Dataset from 79.4% to 82.9%.

Unsupervised Feature Learning for RGB-D Based Object Recognition

Recently introduced RGB-D cameras are capable of providing high quality synchronized videos of both color and depth. With its advanced sensing capabilities, this technology represents an opportunity to dramatically increase the capabilities of object recognition. It also raises the problem of developing expressive features for the color and depth channels of these sensors. In this paper we introduce hierarchical matching pursuit (HMP) for RGB-D data. HMP uses sparse coding to learn hierarchical feature representations from raw RGB-D data in an unsupervised way. Extensive experiments on various datasets indicate that the features learned with our approach enable superior object recognition results using linear support vector machines.

Depth kernel descriptors for object recognition

Consumer depth cameras, such as the Microsoft Kinect, are capable of providing frames of dense depth values at real time. One fundamental question in utilizing depth cameras is how to best extract features from depth frames. Motivated by local descriptors on images, in particular kernel descriptors, we develop a set of kernel features on depth images that model size, 3D shape, and depth edges in a single framework. Through extensive experiments on object recognition, we show that (1) our local features capture different aspects of cues from a depth frame/view that complement one another; (2) our kernel features significantly outperform traditional 3D features (e.g. Spin images); and (3) we significantly improve the capabilities of depth and RGB-D (color+depth) recognition, achieving 10–15% improvement in accuracy over the state of the art.

Sparse distance learning for object recognition combining RGB and depth information

In this work we address joint object category and instance recognition in the context of RGB-D (depth) cameras. Motivated by local distance learning, where a novel view of an object is compared to individual views of previously seen objects, we define a view-to-object distance where a novel view is compared simultaneously to all views of a previous object. This novel distance is based on a weighted combination of feature differences between views. We show, through jointly learning per-view weights, that this measure leads to superior classification performance on object category and instance recognition. More importantly, the proposed distance allows us to find a sparse solution via Group-Lasso regularization, where a small subset of representative views of an object is identified and used, with the rest discarded. This significantly reduces computational cost without compromising recognition accuracy. We evaluate the proposed technique, Instance Distance Learning (IDL), on the RGB-D Object Dataset, which consists of 300 object instances in 51 everyday categories and about 250,000 views of objects with both RGB color and depth. We empirically compare IDL to several alternative state-of-the-art approaches and also validate the use of visual and shape cues and their combination.

Object recognition with hierarchical kernel descriptors

Kernel descriptors [1] provide a unified way to generate rich visual feature sets by turning pixel attributes into patch-level features, and yield impressive results on many object recognition tasks. However, best results with kernel descriptors are achieved using efficient match kernels in conjunction with nonlinear SVMs, which makes it impractical for large-scale problems. In this paper, we propose hierarchical kernel descriptors that apply kernel descriptors recursively to form image-level features and thus provide a conceptually simple and consistent way to generate image-level features from pixel attributes. More importantly, hierarchical kernel descriptors allow linear SVMs to yield state-of-the-art accuracy while being scalable to large datasets. They can also be naturally extended to extract features over depth images. We evaluate hierarchical kernel descriptors both on the CIFAR10 dataset and the new RGB-D Object Dataset consisting of segmented RGB and depth images of 300 everyday objects.

Spectral Clustering Ensemble Applied to SAR Image Segmentation

Spectral clustering (SC) has been used with success in the field of computer vision for data clustering. In this paper, a new algorithm named SC ensemble (SCE) is proposed for the segmentation of synthetic aperture radar (SAR) images. The gray-level cooccurrence matrix-based statistic features and the energy features from the undecimated wavelet decomposition extracted for each pixel being the input, our algorithm performs segmentation by combining multiple SC results as opposed to using outcomes of a single clustering process in the existing literature. The random subspace, random scaling parameter, and Nystrom approximation for component SC are applied to construct the SCE. This technique provides necessary diversity as well as high quality of component learners for an efficient ensemble. It also overcomes the shortcomings faced by the SC, such as the selection of scaling parameter, and the instability resulted from the Nystrom approximation method in image segmentation. Experimental results show that the proposed method is effective for SAR image segmentation and insensitive to the scaling parameter.

Multipath Sparse Coding Using Hierarchical Matching Pursuit

Complex real-world signals, such as images, contain discriminative structures that differ in many aspects including scale, invariance, and data channel. While progress in deep learning shows the importance of learning features through multiple layers, it is equally important to learn features through multiple paths. We propose Multipath Hierarchical Matching Pursuit (M-HMP), a novel feature learning architecture that combines a collection of hierarchical sparse features for image classification to capture multiple aspects of discriminative structures. Our building blocks are MI-KSVD, a codebook learning algorithm that balances the reconstruction error and the mutual incoherence of the codebook, and batch orthogonal matching pursuit (OMP), we apply them recursively at varying layers and scales. The result is a highly discriminative image representation that leads to large improvements to the state-of-the-art on many standard benchmarks, e.g., Caltech-101, Caltech-256, MITScenes, Oxford-IIIT Pet and Caltech-UCSD Bird-200.

Detection-based object labeling in 3D scenes

We propose a view-based approach for labeling objects in 3D scenes reconstructed from RGB-D (color+depth) videos. We utilize sliding window detectors trained from object views to assign class probabilities to pixels in every RGB-D frame. These probabilities are projected into the reconstructed 3D scene and integrated using a voxel representation. We perform efficient inference on a Markov Random Field over the voxels, combining cues from view-based detection and 3D shape, to label the scene. Our detection-based approach produces accurate scene labeling on the RGB-D Scenes Dataset and improves the robustness of object detection.