Integral customer pose estimation using body orientation and visibility mask

Li, Jingwen; Gu, Yanlei; Kamijo, Shunsuke

doi:10.1007/s11042-018-5839-2

Cited by 2 publications

(5 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This proposed algorithm could be used for some applications that need high accuracy but do not require real-time processing speed, e.g., our previously published works [36,40] propose to analyze the customer pose for marketing. The customer behavior analysis is one of the most concerned topics for retailers because the customer behavior information can indicate the customer interest level to the product in the stores and is helpful to increase the commercial benefit.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…Similarly, if a person is facing the camera, his or her right shoulder is probably on the left side of the image. Our previous research [36] suggests that body orientation could be defined as 8 directions, as shown in Figure 6. When the body is defined as 8 directions, the prediction result of the body orientation can be a vector format with 8 elements.…”

Section: Orientation-occlusion Branchmentioning

confidence: 98%

“…Haque et al [17] implicitly learn the occlusion through a deep neural network and gave the output of a visibility mask of joints. In our previous work [36], orientation prediction is integrated with single person pose estimation.…”

Section: Information Used For Human Pose Estimationmentioning

confidence: 99%

“…In addition, the accuracy of non-deep neural network approaches is lower than the following deep neural network approaches [16,18]. The single person pose estimation works with the guarantee of only one person present in the image [16][17][18][19][20][21][22][23][24][25]35,36]. However, the scenes with multi-person are exceedingly common in our daily life.…”

Section: Information Used For Human Pose Estimationmentioning

confidence: 99%

Section: Orientation-occlusion Branchmentioning

confidence: 99%

See 4 more Smart Citations

Multi-Person Pose Estimation using an Orientation and Occlusion Aware Deep Learning Network

Zhang

Kamijo

2020

Sensors

Self Cite

View full text Add to dashboard Cite

Image based human behavior and activity understanding has been a hot topic in the field of computer vision and multimedia. As an important part, skeleton estimation, which is also called pose estimation, has attracted lots of interests. For pose estimation, most of the deep learning approaches mainly focus on the joint feature. However, the joint feature is not sufficient, especially when the image includes multi-person and the pose is occluded or not fully visible. This paper proposes a novel multi-task framework for the multi-person pose estimation. The proposed framework is developed based on Mask Region-based Convolutional Neural Networks (R-CNN) and extended to integrate the joint feature, body boundary, body orientation and occlusion condition together. In order to further improve the performance of the multi-person pose estimation, this paper proposes to organize the different information in serial multi-task models instead of the widely used parallel multi-task network. The proposed models are trained on the public dataset Common Objects in Context (COCO), which is further augmented by ground truths of body orientation and mutual-occlusion mask. Experiments demonstrate the performance of the proposed method for multi-person pose estimation and body orientation estimation. The proposed method can detect 84.6% of the Percentage of Correct Keypoints (PCK) and has an 83.7% Correct Detection Rate (CDR). Comparisons further illustrate the proposed model can reduce the over-detection compared with other methods.

show abstract

Section: Comparison With Other Methodsmentioning

confidence: 99%

Section: Orientation-occlusion Branchmentioning

confidence: 98%