Depth kernel descriptors for object recognition

By Liefeng Bo, Xiaofeng Ren, Dieter Fox. 2011

348 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

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

Citations in the corpus

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection (2017, methodology): “Some of the earlier methods for feature representation are [41, 8, 7, 19, 42, 35, 6, 27, 1, 36, 2, 25, 26].”
RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, methodology): “This new dataset further boosts the research on applications such as category recognition, instance recognition, 3D scene labeling and object pose estimation [9, 10, 53].”
Feature learning based on SAE-PCA network for human gesture recognition in RGBD images (2015, methodology): “Rodriguez et al. [9] proposed a method for ASL recognition using RGB-D information, which combines SIFT feature from intensity image and gradient kernel descriptor [14] from depth image.”
Local structure preserving discriminative projections for RGB-D sensor-based scene classification (2015, methodology): “By considering the spatial layout of features, spatial pyramid matching (SPM) has been utilized in recent state of the art scene classification systems with some success [5,27,50].”
A Joint Model of Language and Perception for Grounded Attribute Learning (2012, methodology): “Our approach builds on existing work on visual attribute classiﬁcation (Bo et al., 2011) and probabilistic categorial grammar induction for semantic parsing (Zettlemoyer & Collins, 2005; Kwiatkowski et al., 2011).”
Object Classification Using CNN-Based Fusion of Vision and LIDAR in Autonomous Vehicle Environment (2018, neutral): “[24].”
Learning hierarchical sparse features for RGB-(D) object recognition (2014, methodology): “This allows us to dramatically reduce the total cost of orthogonal matching pursuit by pre-computing some quantities (Davis et al., 1997; Rubin-stein et al., 2008; Bo et al., 2011c).”
Sliding Shapes for 3D Object Detection in Depth Images (2014, background): “3D classification: Classification-based approaches [65–68, 51, 69–79] typically consider the whole object at the same time by extracting a holistic feature for the whole object and classifying the feature vector via a classifier.”
Hand-Crafted Features or Machine Learnt Features? Together They Improve RGB-D Object Recognition (2014, methodology): “Extending kernel method to depth images and 3D points, depth kernel descriptor is introduced in [4], and the recognition accuracy is much higher than hand-designed method on the RGB-D Object Dataset.”
Multi-modal feature fusion for action recognition in RGB-D sequences (2014, methodology): “A more attentive way to fuse multi-modal features is to build separated kernels for different modalities of the data and apply a multi-kernel learning technique to aggregate their discriminative powers like [5, 6].”
Convolutional-Recursive Deep Learning for 3D Object Classification (2012, methodology): “Table 1 lists the main accuracy numbers and compares to the published results [2, 5, 6, 7].”
Boundary Cues for 3D Object Shape Recovery (2013, methodology): “We also show the results of an RGB classifier using [4].”
Parsing the Hand in Depth Images (2014, background): “, the fast point feature histograms [27], the geodesic distance map [33], and the depth kernel descriptors [34].”
Unsupervised Feature Learning for RGB-D Based Object Recognition (2012, methodology): “However, most state-of-the-art object recognition systems are still based on hand-designed representations (features), such as SIFT [25], Spin Images [17], SURF [2], Fast Point Feature Histogram [27], LINE-MOD [14], or feature combinations [19, 6].”
RGB-(D) scene labeling: Features and algorithms (2012, methodology): “We use and evaluate six kernel descriptors (as in [3]): gradient (G), color (C), local binary pattern (L), depth gradient (GD), spin/surface normal (S), and KPCA/self-similarity (K).”
Recognizing RGB Images by Learning from RGB-D Data (2014, methodology): “Then, we follow [2] to aggregate the kernel descriptors into object-level features, in which we set the vocabulary size as 1000 and use three level of pyramids (i.”