Car make and model recognition using 3D curve alignment

Ramnath, Krishnan; Sinha, Sudipta N.; Szeliski, Richard; Hsiao, Edward

doi:10.1109/wacv.2014.6836087

Cited by 41 publications

(17 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, they only reliably handle textured objects in high resolution images [16]. Other related methods include 3D model-based registration [18,21,36], Hausdorff matching [10], oriented Chamfer matching for edges [19] and 3D chamfer matching for aligning 3D curve-based models to images [27].…”

Section: Related Workmentioning

confidence: 99%

Real-Time Seamless Single Shot 6D Object Pose Prediction

Tekin

Sinha

Fua

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Self Cite

802

546

View full text Add to dashboard Cite

We propose a single-shot approach for simultaneously detecting an object in an RGB image and predicting its 6D pose without requiring multiple stages or having to examine multiple hypotheses. Unlike a recently proposed single-shot technique for this task [11] that only predicts an approximate 6D pose that must then be refined, ours is accurate enough not to require additional post-processing. As a result, it is much faster -50 fps on a Titan X (Pascal) GPU -and more suitable for real-time processing. The key component of our method is a new CNN architecture inspired by [28,29] that directly predicts the 2D image locations of the projected vertices of the object's 3D bounding box. The object's 6D pose is then estimated using a PnP algorithm.For single object and multiple object pose estimation on the LINEMOD and OCCLUSION datasets, our approach substantially outperforms other recent CNN-based approaches [11,26] when they are all used without postprocessing. During post-processing, a pose refinement step can be used to boost the accuracy of these two methods, but at 10 fps or less, they are much slower than our method.

show abstract

Section: Related Workmentioning

confidence: 99%

Real-Time Seamless Single Shot 6D Object Pose Prediction

Tekin

Sinha

Fua

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

Self Cite

802

546

View full text Add to dashboard Cite

show abstract

“…These feature descriptors were designed to be invariant to changes in scale, rotation, illumination and keypoints [2][3][4][5]. Other related approaches involve 3D model-based registration [6,7], and Hausdorff and Chamfer matching for edges and curves [8][9][10]. Such methods are often fast and work reasonably well in cluttered scenes.…”

Section: Related Researchmentioning

confidence: 99%

Ground Plane Polling for 6DoF Pose Estimation of Objects on the Road

Rangesh

Trivedi

2020

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

This paper introduces an approach to produce accurate 3D detection boxes for objects on the ground using single monocular images. We do so by merging 2D visual cues, 3D object dimensions, and ground plane constraints to produce boxes that are robust against small errors and incorrect predictions. First, we train a single-stage convolutional neural network (CNN) that produces multiple visual and geometric cues of interest: 2D bounding boxes, 2D keypoints of interest, coarse object orientations and object dimensions. Subsets of these cues are then used to poll probable ground planes from a pre-computed database of ground planes, to identify the "best fit" plane with highest consensus. Once identified, the "best fit" plane provides enough constraints to successfully construct the desired 3D detection box, without directly predicting the 6DoF pose of the object. The entire ground plane polling (GPP) procedure is constructed as a non-parametrized layer of the CNN that outputs the desired "best fit" plane and the corresponding 3D keypoints, which together define the final 3D bounding box. This single-stage, single-pass CNN results in superior localization and orientation estimation compared to more complex and computationally expensive monocular approaches.

show abstract

“…is the four coordinates of the ground-true box. δ i is a label function in equations (6) and (7). If the label of the prediction box is a positive sample, δ i � 1.…”

Section: Loss Functionmentioning

confidence: 99%

“…In the aspect of vehicle attribute recognition based on 3D models, the Bayesian algorithm is applied to generate a 3D vehicle model for matching the features and realizing the vehicle classi cation [5]. A 3D curve alignment method [6] is established to identify the types of the vehicles from a single image. e image gradient is used to calculate the attitude scores of the targets, and the real-time vehicle location is realized [7].…”

Section: Introductionmentioning

confidence: 99%

Vehicle Attribute Recognition for Normal Targets and Small Targets Based on Multitask Cascaded Network

et al. 2019

View full text Add to dashboard Cite

The interference of the complex background and less information of the small targets are two major problems in vehicle attribute recognition. In this paper, two cascaded networks of vehicle attribute recognition are established to solve the two problems. For vehicle targets with normal size, the multitask cascaded convolution neural network MC-CNN-NT uses the improved Faster R-CNN as the location subnetwork. The vehicle targets in the complex background are extracted by the location subnetwork to the classification subnetwork CNN for the classification. The implementation of this task decomposition strategy effectively eliminates the interference of the complex background in target detection. For vehicle targets with small size, the multitask cascaded convolution neural network MC-CNN-ST applies the network compression strategy and the multilayer feature fusion strategy to extract the feature maps. These strategies enrich the location information and semantic information of the feature maps. In order to optimize the nonlinear mapping ability and the hard-to-detect samples mining ability of the networks, the activation function and the loss function in the two cascaded networks are improved. The experimental results show that MC-CNN-NT for the normal targets and MC-CNN-ST for the small targets achieve the state-of-the-art performance compared with other attribute recognition networks.

show abstract

Car make and model recognition using 3D curve alignment

Cited by 41 publications

References 29 publications

Real-Time Seamless Single Shot 6D Object Pose Prediction

Real-Time Seamless Single Shot 6D Object Pose Prediction

Ground Plane Polling for 6DoF Pose Estimation of Objects on the Road

Vehicle Attribute Recognition for Normal Targets and Small Targets Based on Multitask Cascaded Network

Contact Info

Product

Resources

About