The challenge of simultaneous object detection and pose estimation: A comparative study

Oñoro-Rubio, Daniel; López-Sastre, Roberto J.; Redondo-Cabrera, Carolina; Gil-Jiménez, Pedro

doi:10.1016/j.imavis.2018.09.013

Cited by 15 publications

(10 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was found out that regression works significantly worse. This tendency is also described in [13], especially, when the amount of training images is not large enough.…”

Section: Resultsmentioning

confidence: 75%

“…which embeds the pose estimation within the object detection and classification network. Oñoro-Rubio et al [13] created a set of three approaches that represent similar systems following the separated, the simultaneous and a mixed strategy, working out that a model with separated detection and orientation estimation achieves a higher overall performance. Additionally, some special solutions were created.…”

Section: Related Workmentioning

confidence: 99%

“…Most of the listed approaches are based on previous work about object detection using CNNs. While [8], [16] and [22] utilize a single shot architecture as outlined in [11], the approaches described in [12], [13] and [20] are built upon R-CNN [4] and its successors.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

A Robot Localization Framework Using CNNs for Object Detection and Pose Estimation

Hoyer

Steup

Mostaghim

2018

2018 IEEE Symposium Series on Computational Intelligence (SSCI)

View full text Add to dashboard Cite

External localization is an essential part for the indoor operation of small or cost-efficient robots, as they are used, for example, in swarm robotics. We introduce a two-stage localization and instance identification framework for arbitrary robots based on convolutional neural networks. Object detection is performed on an external camera image of the operation zone providing robot bounding boxes for an identification and orientation estimation convolutional neural network. Additionally, we propose a process to generate the necessary training data. The framework was evaluated with 3 different robot types and various identification patterns. We have analyzed the main framework hyperparameters providing recommendations for the framework operation settings. We achieved up to 98% mAP@IOU0.5 and only 1.6 • orientation error, running with a frame rate of 50 Hz on a GPU.

show abstract

“…It was found out that regression works significantly worse. This tendency is also described in [13], especially, when the amount of training images is not large enough.…”

Section: Resultsmentioning

confidence: 75%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Robot Localization Framework Using CNNs for Object Detection and Pose Estimation

Hoyer

Steup

Mostaghim

2018

2018 IEEE Symposium Series on Computational Intelligence (SSCI)

View full text Add to dashboard Cite

show abstract

“…they set up a multitask network that has separate branches for pose and category label, which are then treated independently. While [27] proposes various network architectures, all of them are variations of shared networks ( Fig. 2b) or independent networks ( Fig.…”

Section: Related Workmentioning

confidence: 99%

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

Mahendran

Ali

Vidal

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Current CNN-based algorithms for recovering the 3D pose of an object in an image assume knowledge about both the object category and its 2D localization in the image. In this paper, we relax one of these constraints and propose to solve the task of joint object category and 3D pose estimation from an image assuming known 2D localization. We design a new architecture for this task composed of a feature network that is shared between subtasks, an object categorization network built on top of the feature network, and a collection of category dependent pose regression networks. We also introduce suitable loss functions and a training method for the new architecture. Experiments on the challenging PASCAL3D+ dataset show state-of-the-art performance in the joint categorization and pose estimation task. Moreover, our performance on the joint task is comparable to the performance of state-of-the-art methods on the simpler 3D pose estimation with known object category task.

show abstract

“…Some recent works also propose to deal with the problem of estimating the viewpoint of the objects (e.g., References [19,20,21,22,23,24,25,26,27]). It is, therefore, a more difficult problem, because in addition to localizing the object, the approach has to estimate a point of view for it.…”

Section: Introductionmentioning

confidence: 99%

Boosting Multi-Vehicle Tracking with a Joint Object Detection and Viewpoint Estimation Sensor

López-Sastre

Herranz-Perdiguero

Guerrero-Gómez-Olmedo³

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

In this work, we address the problem of multi-vehicle detection and tracking for traffic monitoring applications. We preset a novel intelligent visual sensor for tracking-by-detection with simultaneous pose estimation. Essentially, we adapt an Extended Kalman Filter (EKF) to work not only with the detections of the vehicles but also with their estimated coarse viewpoints, directly obtained with the vision sensor. We show that enhancing the tracking with observations of the vehicle pose, results in a better estimation of the vehicles trajectories. For the simultaneous object detection and viewpoint estimation task, we present and evaluate two independent solutions. One is based on a fast GPU implementation of a Histogram of Oriented Gradients (HOG) detector with Support Vector Machines (SVMs). For the second, we adequately modify and train the Faster R-CNN deep learning model, in order to recover from it not only the object localization but also an estimation of its pose. Finally, we publicly release a challenging dataset, the GRAM Road Traffic Monitoring (GRAM-RTM), which has been especially designed for evaluating multi-vehicle tracking approaches within the context of traffic monitoring applications. It comprises more than 700 unique vehicles annotated across more than 40.300 frames of three videos. We expect the GRAM-RTM becomes a benchmark in vehicle detection and tracking, providing the computer vision and intelligent transportation systems communities with a standard set of images, annotations and evaluation procedures for multi-vehicle tracking. We present a thorough experimental evaluation of our approaches with the GRAM-RTM, which will be useful for establishing further comparisons. The results obtained confirm that the simultaneous integration of vehicle localizations and pose estimations as observations in an EKF, improves the tracking results.

show abstract

The challenge of simultaneous object detection and pose estimation: A comparative study

Cited by 15 publications

References 31 publications

A Robot Localization Framework Using CNNs for Object Detection and Pose Estimation

A Robot Localization Framework Using CNNs for Object Detection and Pose Estimation

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

Boosting Multi-Vehicle Tracking with a Joint Object Detection and Viewpoint Estimation Sensor

Contact Info

Product

Resources

About