Convolutional Networks for Object Category and 3D Pose Estimation from 2D Images

Mahendran, Siddharth; Ali, Haider; Vidal, René

doi:10.1007/978-3-030-11009-3_43

Cited by 6 publications

(6 citation statements)

References 30 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use θ = π 6 , which is a default setting in the literature. A popular approach for solving viewpoint estimation is to cast the problem as bin classification by discretiziing the space of (a, e, θ) [37,21,30,19]. Since network architecture governs the performance of a neural network, we re-train the baseline models [37] with more modern network architectures [6].…”

Section: Viewpoint Estimationmentioning

confidence: 99%

StarMap for Category-Agnostic Keypoint and Viewpoint Estimation

Zhou

Karpur

Luo

et al. 2018

Lecture Notes in Computer Science

131

View full text Add to dashboard Cite

Semantic keypoints provide concise abstractions for a variety of visual understanding tasks. Existing methods define semantic keypoints separately for each category with a fixed number of semantic labels in fixed indices. As a result, this keypoint representation is infeasible when objects have a varying number of parts, e.g. chairs with varying number of legs. We propose a category-agnostic keypoint representation, which combines a multi-peak heatmap (StarMap) for all the keypoints and their corresponding features as 3D locations in the canonical viewpoint (CanViewFeature) defined for each instance. Our intuition is that the 3D locations of the keypoints in canonical object views contain rich semantic and compositional information. Using our flexible representation, we demonstrate competitive performance in keypoint detection and localization compared to category-specific state-of-the-art methods. Moreover, we show that when augmented with an additional depth channel (DepthMap) to lift the 2D keypoints to 3D, our representation can achieve state-of-the-art results in viewpoint estimation. Finally, we show that our category-agnostic keypoint representation can be generalized to novel categories.

show abstract

Section: Viewpoint Estimationmentioning

confidence: 99%

StarMap for Category-Agnostic Keypoint and Viewpoint Estimation

Zhou

Karpur

Luo

et al. 2018

Lecture Notes in Computer Science

131

View full text Add to dashboard Cite

show abstract

“…They call this network R-CNN. Later, other researchers modified and used this network to recognise and detect the objects for autonomous driving and object localisation [ 14 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 ]. However, almost all of these networks rely heavily on the textural information of the objects.…”

Section: Related Workmentioning

confidence: 99%

Marker-Less 3d Object Recognition and 6d Pose Estimation for Homogeneous Textureless Objects: An RGB-D Approach

Hajari

Lugo

Sharma

et al. 2020

Sensors

View full text Add to dashboard Cite

The task of recognising an object and estimating its 6d pose in a scene has received considerable attention in recent years. The accessibility and low-cost of consumer RGB-D cameras, make object recognition and pose estimation feasible even for small industrial businesses. An example is the industrial assembly line, where a robotic arm should pick a small, textureless and mostly homogeneous object and place it in a designated location. Despite all the recent advancements of object recognition and pose estimation techniques in natural scenes, the problem remains challenging for industrial parts. In this paper, we present a framework to simultaneously recognise the object’s class and estimate its 6d pose from RGB-D data. The proposed model adapts a global approach, where an object and the Region of Interest (ROI) are first recognised from RGB images. The object’s pose is then estimated from the corresponding depth information. We train various classifiers based on extracted Histogram of Oriented Gradient (HOG) features to detect and recognize the objects. We then perform template matching on the point cloud based on surface normal and Fast Point Feature Histograms (FPFH) to estimate the pose of the object. Experimental results show that our system is quite efficient, accurate and robust to illumination and background changes, even for the challenging objects of Tless dataset. 6d pose estimation; 3d object recognition; textureless objects; homogeneous objects

show abstract

“…Other authors proposed new architecture with a shared feature network, i.e. first a classifier network operated on extracted features, and finally a respective pose regression networks were engaged separately for each of resulting 12 classes [18]. The feature extractor was based on ResNet-50 stages 1 to 4, then 3 additional FC layers were added and trained for each class pose estimation.…”

Section: Related Workmentioning

confidence: 99%

“…Summarizing, we have observed that convolutional networks are able to extract meaningful features from the image, and were also proven to perform accurate regression. It was stated that the same features are useful both for the classification and for localization [10,18], and networks such as VGG performed exceptionally good in both classification and localization competitions [6]. Therefore we aimed at determining and evaluating a DNN architecture performing both tasks at the same time.…”

Section: Related Workmentioning

confidence: 99%

Deep neural networks for human pose estimation from a very low resolution depth image

Szczuko

2019

Multimed Tools Appl

View full text Add to dashboard Cite

The work presented in the paper is dedicated to determining and evaluating the most efficient neural network architecture applied as a multiple regression network localizing human body joints in 3D space based on a single low resolution depth image. The main challenge was to deal with a noisy and coarse representation of the human body, as observed by a depth sensor from a large distance, and to achieve high localization precision. The regression network was expected to reason about relations of body parts based on depth image, and to extract locations of joints, and provide coordinates defining the body pose. The method involved creation of a dataset with 200,000 realistic depth images of a 3D body model, then training and testing numerous architectures including feedforward multilayer perceptron network and deep convolutional neural networks. The results of training and evaluation are included and discussed. The most accurate DNN network was further trained and evaluated on an augmented depth images dataset. The achieved accuracy was similar to a reference Kinect algorithm results, with a great benefit of fast processing speed and significantly lower requirements on sensor resolution, as it used 100 times less pixels than Kinect depth sensor. The method was robust against sensor noise, allowing imprecision of depth measurements. Finally, our results were compared with VGG, MobileNet, and ResNet architectures.

show abstract

Convolutional Networks for Object Category and 3D Pose Estimation from 2D Images

Cited by 6 publications

References 30 publications

StarMap for Category-Agnostic Keypoint and Viewpoint Estimation

StarMap for Category-Agnostic Keypoint and Viewpoint Estimation

Marker-Less 3d Object Recognition and 6d Pose Estimation for Homogeneous Textureless Objects: An RGB-D Approach

Deep neural networks for human pose estimation from a very low resolution depth image

Contact Info

Product

Resources

About