RGB-D Scene Research Articles

Depth Privileged Scene Recognition via Dual Attention Hallucination.

RGB-D scene recognition has achieved promising performance because depth could provide complementary geometric information to RGB images. However, the inaccessibility of depth sensors severely limits RGB-D applications. In this paper, we focus on depth privileged setting, in which depth information is only available during training but not available during testing. Considering that the information obtained from RGB and depth images are complementary while attention is informative and transferable, our idea is using RGB input to hallucinate depth attention. We build our model upon modulated deformable convolutional layer and hallucinate dual attention: post-hoc importance weight and trainable spatial transformation. Specifically, we use modulation (resp., offset) learned from RGB to mimic Grad-CAM (resp., offset) learned from depth, to combine the strength of dual attention. We also design a weighted loss to avoid negative transfer according to the quality of depth attention. Extensive experiments on two benchmarks, i.e., SUN RGB-D and NYUDv2, demonstrate that our method outperforms the state-of-the-art methods for depth privileged scene recognition.

Markerless Navigation System for Orthopaedic Knee Surgery: A Proof of Concept Study

Current computer-assisted surgical navigation systems mainly rely on optical markers screwed into the bone for anatomy tracking. The insertion of these percutaneous markers increases operating complexity and causes additional harm to the patient. A markerless tracking and registration algorithm has recently been proposed to avoid anatomical markers for knee surgery. The femur points were directly segmented from the recorded RGBD scene by a neural network and then registered to a pre-scanned femur model for the real-time pose. However, in a practical setup such a method can produce unreliable registration results, especially in rotation. Furthermore, its potential application in surgical navigation has not been demonstrated. In this paper, we first improved markerless registration accuracy by adopting a bounded-ICP (BICP) technique, where an estimate of the remote hip centre, acquired also in a markerless way, was employed to constrain distal femur alignment. Then, a proof-of-concept markerless navigation system was proposed to assist in typical knee drilling tasks. Two example setups for global anchoring were proposed and tested on a phantom leg. Our BICP-based markerless tracking and registration method has better angular accuracy and stability than the original method, bringing our straightforward, less invasive markerless navigation approach one step closer to clinical application. According to user tests, our proposed optically anchored navigation system achieves comparable accuracy with the state-of-the-art (3.64± 1.49 mm in position and 2.13±0.81° in orientation). Conversely, our visually anchored, optical tracker-free setup has a lower accuracy (5.86± 1.63 mm in position and 4.18±1.44° in orientation), but is more cost-effective and flexible in the operating room.

Automated Sustainable Multi-Object Segmentation and Recognition via Modified Sampling Consensus and Kernel Sliding Perceptron

Object recognition in depth images is challenging and persistent task in machine vision, robotics, and automation of sustainability. Object recognition tasks are a challenging part of various multimedia technologies for video surveillance, human–computer interaction, robotic navigation, drone targeting, tourist guidance, and medical diagnostics. However, the symmetry that exists in real-world objects plays a significant role in perception and recognition of objects in both humans and machines. With advances in depth sensor technology, numerous researchers have recently proposed RGB-D object recognition techniques. In this paper, we introduce a sustainable object recognition framework that is consistent despite any change in the environment, and can recognize and analyze RGB-D objects in complex indoor scenarios. Firstly, after acquiring a depth image, the point cloud and the depth maps are extracted to obtain the planes. Then, the plane fitting model and the proposed modified maximum likelihood estimation sampling consensus (MMLESAC) are applied as a segmentation process. Then, depth kernel descriptors (DKDES) over segmented objects are computed for single and multiple object scenarios separately. These DKDES are subsequently carried forward to isometric mapping (IsoMap) for feature space reduction. Finally, the reduced feature vector is forwarded to a kernel sliding perceptron (KSP) for the recognition of objects. Three datasets are used to evaluate four different experiments by employing a cross-validation scheme to validate the proposed model. The experimental results over RGB-D object, RGB-D scene, and NYUDv1 datasets demonstrate overall accuracies of 92.2%, 88.5%, and 90.5% respectively. These results outperform existing state-of-the-art methods and verify the suitability of the method.

RGBD Scene Flow Estimation with Global Nonrigid and Local Rigid Assumption

RGBD scene flow has attracted increasing attention in the computer vision with the popularity of depth sensor. To estimate the 3D motion of object accurately, a RGBD scene flow estimation method with global nonrigid and local rigid motion assumption is proposed in this paper. Firstly, the preprocessing is implemented, which includes the colour-depth registration and depth image inpainting, to processing holes and noises in the depth image; secondly, the depth image is segmented to obtain different motion regions with different depth values; thirdly, scene flow is estimated based on the global nonrigid and local rigid assumption and spatial-temporal correlation of RGBD information. In the global nonrigid and local rigid assumption, each segmented region is divided into several blocks, and each block has a rigid motion. With this assumption, the interaction of motion from different parts in the same segmented region is avoided, especially the nonrigid object, e.g., a human body. Experiments are implemented on RGBD tracking dataset and deformable 3D reconstruction dataset. The visual comparison shows that the proposed method can distinguish the motion parts from the static parts in the same region better, and the quantitative comparisons proved more accurate scene flow can be obtained.

Precise iterative closest point algorithm for RGB-D data registration with noise and outliers

In this paper, we propose a precise Iterative Closest Point (ICP) algorithm which is a RGB information supplemented registration method based on correntropy measurement, which can overcome noise and outliers to complete precise point cloud registration. Firstly, in order to achieve accurate point set registration of single structure geometry point cloud with a large number of planes information rather than geometry information, we add the RGB information to our initial method as information compensation, which greatly ensure our algorithm could achieve accurate registration. Secondly, due to the noise and outliers existed in RGB-D data can easily cause deviations in registration, in order to achieve precise registration in RGB-D data, we introduced the correntropy measurement method into the initial model. Experimental results on our scene dataset demonstrate the proposed algorithm can achieve precise point set registration in RGB-D scene data well.

An Efficient RGB-D Scene Recognition Method Based on Multi-Information Fusion

RGB-D scene recognition is a challenging problem due to lack of RGB-D datasets and inefficient RGB-D fusion. In this paper, we exploit several factors that affect the RGB-D scene recognition performance, including the representations of the RGB-D data and objects in the scene. We propose an effective multi-information fusion method composed of two modules: a revised detection-based method, and a multi-feature fusion based classifier. The revised detection-based method leverage the auxiliary RGB data. And the multi-feature fusion based classifier select the optimal feature configuration for RGB-D data description. The proposed method is validated on two publicly available datasets: the SUN RGB-D dataset, and the NYU Depth v2 dataset. The obtained results show that the proposed fusion method is effective and is comparable with the state-of-the-art method. Furthermore, the proposed framework contains much less parameters than the state-of-the-art model and thus requires much less time for training. The code and the fine-tuned model parameters are available at: https://github.com/zhangbin28/MulInfo_RGBDScene .

Robotic grasp detection based on image processing and random forest

Real-time grasp detection plays a key role in manipulation, and it is also a complex task, especially for detecting how to grasp novel objects. This paper proposes a very quick and accurate approach to detect robotic grasps. The main idea is to perform grasping of novel objects in a typical RGB-D scene view. Our goal is not to find the best grasp for every object but to obtain the local optimal grasps in candidate grasp rectangles. There are three main contributions to our detection work. Firstly, an improved graph segmentation approach is used to do objects detection and it can separate objects from the background directly and fast. Secondly, we develop a morphological image processing method to generate candidate grasp rectangles set which avoids us to search grasp rectangles globally. Finally, we train a random forest model to predict grasps and achieve an accuracy of 94.26%. The model is mainly used to score every element in our candidate grasps set and the one gets the highest score will be converted to the final grasp configuration for robots. For real-world experiments, we set up our system on a tabletop scene with multiple objects and when implementing robotic grasps, we control Baxter robot with a different inverse kinematics strategy rather than the built-in one.

MSN: Modality separation networks for RGB-D scene recognition

RGB-D image based indoor scene recognition is a challenging task due to the complex scene layouts and cluttered objects. Although the depth modality can provide extra geometric information, how to better learn the multi-modal features is still an open problem. Considering this, in this paper we propose the modality separation networks to extract the modal-consistent and modal-specific features simultaneously. The motivations of this work are from two aspects: 1) The first one is to learn what is unique to each modality and what is common between the two modalities explicitly; 2) The second one is to explore the relationship between global/local features and modal-specific/consistent features. To this end, the proposed framework contains two branches of submodules to learn the multi-modal features. One branch is used to extract the individual characteristics of each modality by minimizing the similarity between two modalities. Another branch is to learn the common information between two modalities by maximizing the correlation term. Moreover, with the spatial attention module, our method can visualize the spatial positions where different submodules focus on. We evaluate our method on two public RGB-D scene recognition datasets, and new state-of-the-art results are achieved with the proposed framework.

Image Representations with Spatial Object-to-Object Relations for RGB-D Scene Recognition.

Scene recognition is challenging due to the intra-class diversity and inter-class similarity. Previous works recognize scenes either with global representations or with the intermediate representations of objects. In contrast, we investigate more discriminative image representations of object-to-object relations for scene recognition, which are based on the triplets of <object, relation, object> obtained with detection techniques. Particularly, two types of representations, including co-occurring frequency of object-to-object relation (denoted as COOR) and sequential representation of object-to-object relation (denoted as SOOR), are proposed to describe objects and their relative relations in different forms. COOR is represented as the intermediate representation of co-occurring frequency of objects and their relations, with a three order tensor that can be fed to scene classifier without further embedding. SOOR is represented in a more explicit and freer form that sequentially describe image contents with local captions. And a sequence encoding model (e.g., recurrent neural network (RNN)) is implemented to encode SOOR to the features for feeding the classifiers. In order to better capture the spatial information, the proposed COOR and SOOR are adapted to RGB-D data, where a RGB-D proposal fusion method is proposed for RGB-D object detection. With the proposed approaches COOR and SOOR, we obtain the state-of-the-art results of RGB-D scene recognition on SUN RGB-D and NYUD2 datasets.

ACM: Adaptive Cross-Modal Graph Convolutional Neural Networks for RGB-D Scene Recognition

RGB image classification has achieved significant performance improvement with the resurge of deep convolutional neural networks. However, mono-modal deep models for RGB image still have several limitations when applied to RGB-D scene recognition. 1) Images for scene classification usually contain more than one typical object with flexible spatial distribution, so the object-level local features should also be considered in addition to global scene representation. 2) Multi-modal features in RGB-D scene classification are still under-utilized. Simply combining these modal-specific features suffers from the semantic gaps between different modalities. 3) Most existing methods neglect the complex relationships among multiple modality features. Considering these limitations, this paper proposes an adaptive crossmodal (ACM) feature learning framework based on graph convolutional neural networks for RGB-D scene recognition. In order to make better use of the modal-specific cues, this approach mines the intra-modality relationships among the selected local features from one modality. To leverage the multi-modal knowledge more effectively, the proposed approach models the inter-modality relationships between two modalities through the cross-modal graph (CMG). We evaluate the proposed method on two public RGB-D scene classification datasets: SUN-RGBD and NYUD V2, and the proposed method achieves state-of-the-art performance.

Joint Task-Recursive Learning for RGB-D Scene Understanding.

RGB-D scene understanding under monocular camera is an emerging and challenging topic with many potential applications. In this paper, we propose a novel Task-Recursive Learning (TRL) framework to jointly and recurrently conduct three representative tasks therein containing depth estimation, surface normal prediction and semantic segmentation. TRL recursively refines the prediction results through a series of task-level interactions, where one-time cross-task interaction is abstracted as one network block of one time stage. In each stage, we serialize multiple tasks into a sequence and then recursively perform their interactions. To adaptively enhance counterpart patterns, we encapsulate interactions into a specific Task-Attentional Module (TAM) to mutually-boost the tasks from each other. Across stages, the historical experiences of previous states of tasks are selectively propagated into the next stages by using Feature-Selection unit (FS-Unit), which takes advantage of complementary information across tasks. The sequence of task-level interactions is also evolved along a coarse-to-fine scale space such that the required details may be refined progressively. Finally the task-abstracted sequence problem of multi-task prediction is framed into a recursive network. Extensive experiments on NYU-Depth v2 and SUN RGB-D datasets demonstrate that our method can recursively refines the results of the triple tasks and achieves state-of-the-art performance.

Deep Multi-View Learning using Neuron-Wise Correlation-Maximizing Regularizers.

Many machine learning problems concern with discovering or associating common patterns in data of multiple views or modalities. Multi-view learning is of the methods to achieve such goals. Recent methods propose deep multi-view networks via adaptation of generic Deep Neural Networks (DNNs), which concatenate features of individual views at intermediate network layers (i.e., fusion layers). In this work, we study the problem of multi-view learning in such end-to-end networks. We take a regularization approach via multi-view learning criteria, and propose a novel, effective, and efficient neuron-wise correlation-maximizing regularizer. We implement our proposed regularizers collectively as a correlation-regularized network layer (CorrReg). CorrReg can be applied to either fully-connected or convolutional fusion layers, simply by replacing them with their CorrReg counterparts. By partitioning neurons of a hidden layer in generic DNNs into multiple subsets, we also consider a multi-view feature learning perspective of generic DNNs. Such a perspective enables us to study deep multi-view learning in the context of regularized network training, for which we present control experiments of benchmark image classification to show the efficacy of our proposed CorrReg. To investigate how CorrReg is useful for practical multi-view learning problems, we conduct experiments of RGB-D object/scene recognition and multi-view based 3D object recognition, using networks with fusion layers that concatenate intermediate features of individual modalities or views for subsequent classification. Applying CorrReg to fusion layers of these networks consistently improves classification performance. In particular, we achieve the new state of the art on the benchmark RGB-D object and RGB-D scene datasets. We make the implementation of CorrReg publicly available.

MAPNet: Multi-modal attentive pooling network for RGB-D indoor scene classification

RGB-D indoor scene classification is an essential and challenging task. Although convolutional neural network (CNN) achieves excellent results on RGB-D object recognition, it has several limitations when extended towards RGB-D indoor scene classification. 1) The semantic cues such as objects of the indoor scene have high spatial variabilities. The spatially rigid global representation from CNN is suboptimal. 2) The cluttered indoor scene has lots of redundant and noisy semantic cues; thus discerning discriminative information among them should not be ignored. 3) Directly concatenating or summing global RGB and Depth information as presented in popular methods cannot fully exploit the complementarity between two modalities for complicated indoor scenarios. To address the above problems, we propose a novel unified framework named Multi-modal Attentive Pooling Network (MAPNet) in this paper. Two orderless attentive pooling blocks are constructed in MAPNet to aggregate semantic cues within and between modalities meanwhile maintain the spatial invariance. The Intra-modality Attentive Pooling (IAP) block aims to mine and pool discriminative semantic cues in each modality. The Cross-modality Attentive Pooling (CAP) block is extended to learn different contributions across two modalities, which further guides the pooling of the selected discriminative semantic cues of each modality. We further show that the proposed model is interpretable, which helps to understand mechanisms of both scene classification and multi-modal fusion in MAPNet. Extensive experiments and analysis on SUN RGB-D Dataset and NYU Depth Dataset V2 show the superiority of MAPNet over current state-of-the-art methods.

RGB-D Scene Recognition via Spatial-Related Multi-Modal Feature Learning

RGB-D image-based scene recognition has achieved significant performance improvement with the development of deep learning methods. While convolutional neural networks can learn high-semantic level features for object recognition, these methods still have limitations for RGB-D scene classification. One limitation is that how to learn better multi-modal features for the RGB-D scene recognition is still an open problem. Another limitation is that the scene images are usually not object-centric and with great spatial variability. Thus, vanilla full-image CNN features maybe not optimal for scene recognition. Considering these problems, in this paper, we propose a compact and effective framework for RGB-D scene recognition. Specifically, we make the following contributions: 1) A novel RGB-D scene recognition framework is proposed to explicitly learn the global modal-specific and local modal-consistent features simultaneously. Different from existing approaches, local CNN features are considered for the learning of modal-consistent representations; 2) key Feature Selection (KFS) module is designed, which can adaptively select important local features from the high-semantic level CNN feature maps. It is more efficient and effective than object detection and dense patch-sampling based methods, and; 3) a triplet correlation loss and a spatial-attention similarity loss are proposed for the training of KFS module. Under the supervision of the proposed loss functions, the network can learn import local features of two modalities with no need for extra annotations. Finally, by concatenating the global and local features together, the proposed framework can achieve new state-of-the-art scene recognition performance on the SUN RGB-D dataset and NYU Depth version 2 (NYUD v2) dataset.

Robust and Efficient CPU-Based RGB-D Scene Reconstruction.

3D scene reconstruction is an important topic in computer vision. A complete scene is reconstructed from views acquired along the camera trajectory, each view containing a small part of the scene. Tracking in textureless scenes is well known to be a Gordian knot of camera tracking, and how to obtain accurate 3D models quickly is a major challenge for existing systems. For the application of robotics, we propose a robust CPU-based approach to reconstruct indoor scenes efficiently with a consumer RGB-D camera. The proposed approach bridges feature-based camera tracking and volumetric-based data integration together and has a good reconstruction performance in terms of both robustness and efficiency. The key points in our approach include: (i) a robust and fast camera tracking method combining points and edges, which improves tracking stability in textureless scenes; (ii) an efficient data fusion strategy to select camera views and integrate RGB-D images on multiple scales, which enhances the efficiency of volumetric integration; (iii) a novel RGB-D scene reconstruction system, which can be quickly implemented on a standard CPU. Experimental results demonstrate that our approach reconstructs scenes with higher robustness and efficiency compared to state-of-the-art reconstruction systems.

Motion-Based Object Segmentation Based on Dense RGB-D Scene Flow

Given two consecutive RGB-D images, we propose a model that estimates a dense 3D motion field, also known as scene flow. We take advantage of the fact that in robot manipulation scenarios, scenes often consist of a set of rigidly moving objects. Our model jointly estimates (i) the segmentation of the scene into an unknown but finite number of objects, (ii) the motion trajectories of these objects and (iii) the object scene flow. We employ an hourglass, deep neural network architecture. In the encoding stage, the RGB and depth images undergo spatial compression and correlation. In the decoding stage, the model outputs three images containing a per-pixel estimate of the corresponding object center as well as object translation and rotation. This forms the basis for inferring the object segmentation and final object scene flow. To evaluate our model, we generated a new and challenging, large-scale, synthetic dataset that is specifically targeted at robotic manipulation: It contains a large number of scenes with a very diverse set of simultaneously moving 3D objects and is recorded with a simulated, static RGB-D camera. In quantitative experiments, we show that we outperform state-of-the-art scene flow and motion-segmentation methods on this data set. In qualitative experiments, we show how our learned model transfers to challenging real-world scenes, visually generating better results than existing methods.

Learning Effective RGB-D Representations for Scene Recognition.

Deep convolutional networks (CNN) can achieve impressive results on RGB scene recognition thanks to large datasets such as Places. In contrast, RGB-D scene recognition is still underdeveloped in comparison, due to two limitations of RGB-D data we address in this paper. The first limitation is the lack of depth data for training deep learning models. Rather than fine tuning or transferring RGB-specific features, we address this limitation by proposing an architecture and a twostep training approach that directly learns effective depth-specific features using weak supervision via patches. The resulting RGBD model also benefits from more complementary multimodal features. Another limitation is the short range of depth sensors (typically 0.5m to 5.5m), resulting in depth images not capturing distant objects in the scenes that RGB images can. We show that this limitation can be addressed by using RGB-D videos, where more comprehensive depth information is accumulated as the camera travels across the scenes. Focusing on this scenario, we introduce the ISIA RGB-D video dataset to evaluate RGB-D scene recognition with videos. Our video recognition architecture combines convolutional and recurrent neural networks (RNNs) that are trained in three steps with increasingly complex data to learn effective features (i.e. patches, frames and sequences). Our approach obtains state-of-the-art performances on RGB-D image (NYUD2 and SUN RGB-D) and video (ISIA RGB-D) scene recognition.

RGB-D Scene Classification via Multi-modal Feature Learning

Most of the past deep learning methods which are proposed for RGB-D scene classification use global information and directly consider all pixels in the whole image for high-level tasks. Such methods cannot hold much information about local feature distributions, and simply concatenate RGB and depth features without exploring the correlation and complementarity between raw RGB and depth images. From the human vision perspective, we recognize the category of one unknown scene mainly relying on the object-level information in the scene which includes the appearance, texture, shape, and depth. The structural distribution of different objects is also taken into consideration. Based on this observation, constructing mid-level representations with discriminative object parts would generally be more attractive for scene analysis. In this paper, we propose a new Convolutional Neural Networks (CNNs)-based local multi-modal feature learning framework (LM-CNN) for RGB-D scene classification. This method can effectively capture much of the local structure from the RGB-D scene images and automatically learn a fusion strategy for the object-level recognition step instead of simply training a classifier on top of features extracted from both modalities. The experimental results on two popular datasets, i.e., NYU v1 depth dataset and SUN RGB-D dataset, show that our method with local multi-modal CNNs outperforms state-of-the-art methods.

Viewpoint invariant semantic object and scene categorization with RGB-D sensors

Understanding the semantics of objects and scenes using multi-modal RGB-D sensors serves many robotics applications. Key challenges for accurate RGB-D image recognition are the scarcity of training data, variations due to viewpoint changes and the heterogeneous nature of the data. We address these problems and propose a generic deep learning framework based on a pre-trained convolutional neural network, as a feature extractor for both the colour and depth channels. We propose a rich multi-scale feature representation, referred to as convolutional hypercube pyramid (HP-CNN), that is able to encode discriminative information from the convolutional tensors at different levels of detail. We also present a technique to fuse the proposed HP-CNN with the activations of fully connected neurons based on an extreme learning machine classifier in a late fusion scheme which leads to a highly discriminative and compact representation. To further improve performance, we devise HP-CNN-T which is a view-invariant descriptor extracted from a multi-view 3D object pose (M3DOP) model. M3DOP is learned from over 140,000 RGB-D images that are synthetically generated by rendering CAD models from different viewpoints. Extensive evaluations on four RGB-D object and scene recognition datasets demonstrate that our HP-CNN and HP-CNN-T consistently outperforms state-of-the-art methods for several recognition tasks by a significant margin.

Multimodal Recurrent Neural Networks With Information Transfer Layers for Indoor Scene Labeling

This paper proposes a new method called Multimodal RNNs for RGB-D scene semantic segmentation. It is optimized to classify image pixels given two input sources: RGB color channels and Depth maps. It simultaneously performs training of two recurrent neural networks (RNNs) that are crossly connected through information transfer layers, which are learnt to adaptively extract relevant cross-modality features. Each RNN model learns its representations from its own previous hidden states and transferred patterns from the other RNNs previous hidden states; thus, both model-specific and crossmodality features are retained. We exploit the structure of quad-directional 2D-RNNs to model the short and long range contextual information in the 2D input image. We carefully designed various baselines to efficiently examine our proposed model structure. We test our Multimodal RNNs method on popular RGB-D benchmarks and show how it outperforms previous methods significantly and achieves competitive results with other state-of-the-art works.