Annotating human poses in realistic scenes is very time consuming, yet necessary for training human pose estimators. We propose to address this problem in an active learning framework, which alternates between requesting the most useful annotations among a large set of unlabelled images, and re-training the pose estimator. To this end, (1) we propose an uncertainty estimator specific for body joint predictions, which takes into account the spatial distribution of the responses of the current pose estimator on the unlabelled images; (2) we propose a dynamic combination of influence and uncertainty cues, where their weights vary during the active learning process according to the reliability of the current pose estimator; (3) we introduce a computer assisted annotation interface, which reduces the time necessary for a human annotator to click on a joint by discretizing the image into regions generated by the current pose estimator. Experiments using the MPII and LSP datasets with both simulated and real annotators show that (1) the proposed active selection scheme outperforms several baselines; (2) our computer-assisted interface can further reduce annotation effort; and (3) our technique can further improve the performance of a pose estimator even when starting from an already strong one.
{"title":"Active Learning for Human Pose Estimation","authors":"Buyu Liu, V. Ferrari","doi":"10.1109/ICCV.2017.468","DOIUrl":"https://doi.org/10.1109/ICCV.2017.468","url":null,"abstract":"Annotating human poses in realistic scenes is very time consuming, yet necessary for training human pose estimators. We propose to address this problem in an active learning framework, which alternates between requesting the most useful annotations among a large set of unlabelled images, and re-training the pose estimator. To this end, (1) we propose an uncertainty estimator specific for body joint predictions, which takes into account the spatial distribution of the responses of the current pose estimator on the unlabelled images; (2) we propose a dynamic combination of influence and uncertainty cues, where their weights vary during the active learning process according to the reliability of the current pose estimator; (3) we introduce a computer assisted annotation interface, which reduces the time necessary for a human annotator to click on a joint by discretizing the image into regions generated by the current pose estimator. Experiments using the MPII and LSP datasets with both simulated and real annotators show that (1) the proposed active selection scheme outperforms several baselines; (2) our computer-assisted interface can further reduce annotation effort; and (3) our technique can further improve the performance of a pose estimator even when starting from an already strong one.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"28 1","pages":"4373-4382"},"PeriodicalIF":0.0,"publicationDate":"2017-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84362176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Oscar Alejandro Mendez Maldonado, Simon Hadfield, N. Pugeault, R. Bowden
Reconstruction of 3D environments is a problem that has been widely addressed in the literature. While many approaches exist to perform reconstruction, few of them take an active role in deciding where the next observations should come from. Furthermore, the problem of travelling from the camera's current position to the next, known as pathplanning, usually focuses on minimising path length. This approach is ill-suited for reconstruction applications, where learning about the environment is more valuable than speed of traversal. We present a novel Scenic Route Planner that selects paths which maximise information gain, both in terms of total map coverage and reconstruction accuracy. We also introduce a new type of collaborative behaviour into the planning stage called opportunistic collaboration, which allows sensors to switch between acting as independent Structure from Motion (SfM) agents or as a variable baseline stereo pair. We show that Scenic Planning enables similar performance to state-of-the-art batch approaches using less than 0.00027% of the possible stereo pairs (3% of the views). Comparison against length-based pathplanning approaches show that our approach produces more complete and more accurate maps with fewer frames. Finally, we demonstrate the Scenic Pathplanner's ability to generalise to live scenarios by mounting cameras on autonomous ground-based sensor platforms and exploring an environment.
{"title":"Taking the Scenic Route to 3D: Optimising Reconstruction from Moving Cameras","authors":"Oscar Alejandro Mendez Maldonado, Simon Hadfield, N. Pugeault, R. Bowden","doi":"10.1109/ICCV.2017.501","DOIUrl":"https://doi.org/10.1109/ICCV.2017.501","url":null,"abstract":"Reconstruction of 3D environments is a problem that has been widely addressed in the literature. While many approaches exist to perform reconstruction, few of them take an active role in deciding where the next observations should come from. Furthermore, the problem of travelling from the camera's current position to the next, known as pathplanning, usually focuses on minimising path length. This approach is ill-suited for reconstruction applications, where learning about the environment is more valuable than speed of traversal. We present a novel Scenic Route Planner that selects paths which maximise information gain, both in terms of total map coverage and reconstruction accuracy. We also introduce a new type of collaborative behaviour into the planning stage called opportunistic collaboration, which allows sensors to switch between acting as independent Structure from Motion (SfM) agents or as a variable baseline stereo pair. We show that Scenic Planning enables similar performance to state-of-the-art batch approaches using less than 0.00027% of the possible stereo pairs (3% of the views). Comparison against length-based pathplanning approaches show that our approach produces more complete and more accurate maps with fewer frames. Finally, we demonstrate the Scenic Pathplanner's ability to generalise to live scenarios by mounting cameras on autonomous ground-based sensor platforms and exploring an environment.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"4 1","pages":"4687-4695"},"PeriodicalIF":0.0,"publicationDate":"2017-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87564983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Guosheng Hu, Yang Hua, Yang Yuan, Zhihong Zhang, Zheng Lu, S. Mukherjee, Timothy M. Hospedales, N. Robertson, Yongxin Yang
Deep learning has achieved great success in face recognition, however deep-learned features still have limited invariance to strong intra-personal variations such as large pose changes. It is observed that some facial attributes (e.g. eyebrow thickness, gender) are robust to such variations. We present the first work to systematically explore how the fusion of face recognition features (FRF) and facial attribute features (FAF) can enhance face recognition performance in various challenging scenarios. Despite the promise of FAF, we find that in practice existing fusion methods fail to leverage FAF to boost face recognition performance in some challenging scenarios. Thus, we develop a powerful tensor-based framework which formulates feature fusion as a tensor optimisation problem. It is nontrivial to directly optimise this tensor due to the large number of parameters to optimise. To solve this problem, we establish a theoretical equivalence between low-rank tensor optimisation and a two-stream gated neural network. This equivalence allows tractable learning using standard neural network optimisation tools, leading to accurate and stable optimisation. Experimental results show the fused feature works better than individual features, thus proving for the first time that facial attributes aid face recognition. We achieve state-of-the-art performance on three popular databases: MultiPIE (cross pose, lighting and expression), CASIA NIR-VIS2.0 (cross-modality environment) and LFW (uncontrolled environment).
{"title":"Attribute-Enhanced Face Recognition with Neural Tensor Fusion Networks","authors":"Guosheng Hu, Yang Hua, Yang Yuan, Zhihong Zhang, Zheng Lu, S. Mukherjee, Timothy M. Hospedales, N. Robertson, Yongxin Yang","doi":"10.1109/ICCV.2017.404","DOIUrl":"https://doi.org/10.1109/ICCV.2017.404","url":null,"abstract":"Deep learning has achieved great success in face recognition, however deep-learned features still have limited invariance to strong intra-personal variations such as large pose changes. It is observed that some facial attributes (e.g. eyebrow thickness, gender) are robust to such variations. We present the first work to systematically explore how the fusion of face recognition features (FRF) and facial attribute features (FAF) can enhance face recognition performance in various challenging scenarios. Despite the promise of FAF, we find that in practice existing fusion methods fail to leverage FAF to boost face recognition performance in some challenging scenarios. Thus, we develop a powerful tensor-based framework which formulates feature fusion as a tensor optimisation problem. It is nontrivial to directly optimise this tensor due to the large number of parameters to optimise. To solve this problem, we establish a theoretical equivalence between low-rank tensor optimisation and a two-stream gated neural network. This equivalence allows tractable learning using standard neural network optimisation tools, leading to accurate and stable optimisation. Experimental results show the fused feature works better than individual features, thus proving for the first time that facial attributes aid face recognition. We achieve state-of-the-art performance on three popular databases: MultiPIE (cross pose, lighting and expression), CASIA NIR-VIS2.0 (cross-modality environment) and LFW (uncontrolled environment).","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"31 1","pages":"3764-3773"},"PeriodicalIF":0.0,"publicationDate":"2017-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85155509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A vast majority of consumer cameras operate the rolling shutter mechanism, which often produces distorted images due to inter-row delay while capturing an image. Recent methods for monocular rolling shutter compensation utilize blur kernel, straightness of line segments, as well as angle and length preservation. However, they do not incorporate scene geometry explicitly for rolling shutter correction, therefore, information about the 3D scene geometry is often distorted by the correction process. In this paper we propose a novel method which leverages geometric properties of the scene—in particular vanishing directions—to estimate the camera motion during rolling shutter exposure from a single distorted image. The proposed method jointly estimates the orthogonal vanishing directions and the rolling shutter camera motion. We performed extensive experiments on synthetic and real datasets which demonstrate the benefits of our approach both in terms of qualitative and quantitative results (in terms of a geometric structure fitting) as well as with respect to computation time.
{"title":"Rolling Shutter Correction in Manhattan World","authors":"Pulak Purkait, C. Zach, A. Leonardis","doi":"10.1109/ICCV.2017.101","DOIUrl":"https://doi.org/10.1109/ICCV.2017.101","url":null,"abstract":"A vast majority of consumer cameras operate the rolling shutter mechanism, which often produces distorted images due to inter-row delay while capturing an image. Recent methods for monocular rolling shutter compensation utilize blur kernel, straightness of line segments, as well as angle and length preservation. However, they do not incorporate scene geometry explicitly for rolling shutter correction, therefore, information about the 3D scene geometry is often distorted by the correction process. In this paper we propose a novel method which leverages geometric properties of the scene—in particular vanishing directions—to estimate the camera motion during rolling shutter exposure from a single distorted image. The proposed method jointly estimates the orthogonal vanishing directions and the rolling shutter camera motion. We performed extensive experiments on synthetic and real datasets which demonstrate the benefits of our approach both in terms of qualitative and quantitative results (in terms of a geometric structure fitting) as well as with respect to computation time.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"53 1","pages":"882-890"},"PeriodicalIF":0.0,"publicationDate":"2017-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83098527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Laurie Bose, Jianing Chen, S. Carey, P. Dudek, W. Mayol-Cuevas
We present an approach of estimating constrained egomotion on a Pixel Processor Array (PPA). These devices embed processing and data storage capability into the pixels of the image sensor, allowing for fast and low power parallel computation directly on the image-plane. Rather than the standard visual pipeline whereby whole images are transferred to an external general processing unit, our approach performs all computation upon the PPA itself, with the camera's estimated motion as the only information output. Our approach estimates 3D rotation and a 1D scale-less estimate of translation. We introduce methods of image scaling, rotation and alignment which are performed solely upon the PPA itself and form the basis for conducting motion estimation. We demonstrate the algorithms on a SCAMP-5 vision chip, achieving frame rates >1000Hz at ~2W power consumption.
{"title":"Visual Odometry for Pixel Processor Arrays","authors":"Laurie Bose, Jianing Chen, S. Carey, P. Dudek, W. Mayol-Cuevas","doi":"10.1109/ICCV.2017.493","DOIUrl":"https://doi.org/10.1109/ICCV.2017.493","url":null,"abstract":"We present an approach of estimating constrained egomotion on a Pixel Processor Array (PPA). These devices embed processing and data storage capability into the pixels of the image sensor, allowing for fast and low power parallel computation directly on the image-plane. Rather than the standard visual pipeline whereby whole images are transferred to an external general processing unit, our approach performs all computation upon the PPA itself, with the camera's estimated motion as the only information output. Our approach estimates 3D rotation and a 1D scale-less estimate of translation. We introduce methods of image scaling, rotation and alignment which are performed solely upon the PPA itself and form the basis for conducting motion estimation. We demonstrate the algorithms on a SCAMP-5 vision chip, achieving frame rates >1000Hz at ~2W power consumption.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"99 1","pages":"4614-4622"},"PeriodicalIF":0.0,"publicationDate":"2017-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77212750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vicky S. Kalogeiton, Philippe Weinzaepfel, V. Ferrari, C. Schmid
While most existing approaches for detection in videos focus on objects or human actions separately, we aim at jointly detecting objects performing actions, such as cat eating or dog jumping. We introduce an end-to-end multitask objective that jointly learns object-action relationships. We compare it with different training objectives, validate its effectiveness for detecting objects-actions in videos, and show that both tasks of object and action detection benefit from this joint learning. Moreover, the proposed architecture can be used for zero-shot learning of actions: our multitask objective leverages the commonalities of an action performed by different objects, e.g. dog and cat jumping, enabling to detect actions of an object without training with these object-actions pairs. In experiments on the A2D dataset [50], we obtain state-of-the-art results on segmentation of object-action pairs. We finally apply our multitask architecture to detect visual relationships between objects in images of the VRD dataset [24].
{"title":"Joint Learning of Object and Action Detectors","authors":"Vicky S. Kalogeiton, Philippe Weinzaepfel, V. Ferrari, C. Schmid","doi":"10.1109/ICCV.2017.219","DOIUrl":"https://doi.org/10.1109/ICCV.2017.219","url":null,"abstract":"While most existing approaches for detection in videos focus on objects or human actions separately, we aim at jointly detecting objects performing actions, such as cat eating or dog jumping. We introduce an end-to-end multitask objective that jointly learns object-action relationships. We compare it with different training objectives, validate its effectiveness for detecting objects-actions in videos, and show that both tasks of object and action detection benefit from this joint learning. Moreover, the proposed architecture can be used for zero-shot learning of actions: our multitask objective leverages the commonalities of an action performed by different objects, e.g. dog and cat jumping, enabling to detect actions of an object without training with these object-actions pairs. In experiments on the A2D dataset [50], we obtain state-of-the-art results on segmentation of object-action pairs. We finally apply our multitask architecture to detect visual relationships between objects in images of the VRD dataset [24].","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"36 1","pages":"2001-2010"},"PeriodicalIF":0.0,"publicationDate":"2017-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85857365","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Collomosse, Tu Bui, Michael J. Wilber, Chen Fang, Hailin Jin
We propose a novel measure of visual similarity for image retrieval that incorporates both structural and aesthetic (style) constraints. Our algorithm accepts a query as sketched shape, and a set of one or more contextual images specifying the desired visual aesthetic. A triplet network is used to learn a feature embedding capable of measuring style similarity independent of structure, delivering significant gains over previous networks for style discrimination. We incorporate this model within a hierarchical triplet network to unify and learn a joint space from two discriminatively trained streams for style and structure. We demonstrate that this space enables, for the first time, styleconstrained sketch search over a diverse domain of digital artwork comprising graphics, paintings and drawings. We also briefly explore alternative query modalities.
{"title":"Sketching with Style: Visual Search with Sketches and Aesthetic Context","authors":"J. Collomosse, Tu Bui, Michael J. Wilber, Chen Fang, Hailin Jin","doi":"10.1109/ICCV.2017.290","DOIUrl":"https://doi.org/10.1109/ICCV.2017.290","url":null,"abstract":"We propose a novel measure of visual similarity for image retrieval that incorporates both structural and aesthetic (style) constraints. Our algorithm accepts a query as sketched shape, and a set of one or more contextual images specifying the desired visual aesthetic. A triplet network is used to learn a feature embedding capable of measuring style similarity independent of structure, delivering significant gains over previous networks for style discrimination. We incorporate this model within a hierarchical triplet network to unify and learn a joint space from two discriminatively trained streams for style and structure. We demonstrate that this space enables, for the first time, styleconstrained sketch search over a diverse domain of digital artwork comprising graphics, paintings and drawings. We also briefly explore alternative query modalities.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"8 1","pages":"2679-2687"},"PeriodicalIF":0.0,"publicationDate":"2017-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84133489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jifei Song, Qian Yu, Yi-Zhe Song, T. Xiang, Timothy M. Hospedales
Human sketches are unique in being able to capture both the spatial topology of a visual object, as well as its subtle appearance details. Fine-grained sketch-based image retrieval (FG-SBIR) importantly leverages on such fine-grained characteristics of sketches to conduct instance-level retrieval of photos. Nevertheless, human sketches are often highly abstract and iconic, resulting in severe misalignments with candidate photos which in turn make subtle visual detail matching difficult. Existing FG-SBIR approaches focus only on coarse holistic matching via deep cross-domain representation learning, yet ignore explicitly accounting for fine-grained details and their spatial context. In this paper, a novel deep FG-SBIR model is proposed which differs significantly from the existing models in that: (1) It is spatially aware, achieved by introducing an attention module that is sensitive to the spatial position of visual details: (2) It combines coarse and fine semantic information via a shortcut connection fusion block: and (3) It models feature correlation and is robust to misalignments between the extracted features across the two domains by introducing a novel higher-order learnable energy function (HOLEF) based loss. Extensive experiments show that the proposed deep spatial-semantic attention model significantly outperforms the state-of-the-art.
{"title":"Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval","authors":"Jifei Song, Qian Yu, Yi-Zhe Song, T. Xiang, Timothy M. Hospedales","doi":"10.1109/ICCV.2017.592","DOIUrl":"https://doi.org/10.1109/ICCV.2017.592","url":null,"abstract":"Human sketches are unique in being able to capture both the spatial topology of a visual object, as well as its subtle appearance details. Fine-grained sketch-based image retrieval (FG-SBIR) importantly leverages on such fine-grained characteristics of sketches to conduct instance-level retrieval of photos. Nevertheless, human sketches are often highly abstract and iconic, resulting in severe misalignments with candidate photos which in turn make subtle visual detail matching difficult. Existing FG-SBIR approaches focus only on coarse holistic matching via deep cross-domain representation learning, yet ignore explicitly accounting for fine-grained details and their spatial context. In this paper, a novel deep FG-SBIR model is proposed which differs significantly from the existing models in that: (1) It is spatially aware, achieved by introducing an attention module that is sensitive to the spatial position of visual details: (2) It combines coarse and fine semantic information via a shortcut connection fusion block: and (3) It models feature correlation and is robust to misalignments between the extracted features across the two domains by introducing a novel higher-order learnable energy function (HOLEF) based loss. Extensive experiments show that the proposed deep spatial-semantic attention model significantly outperforms the state-of-the-art.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"35 1","pages":"5552-5561"},"PeriodicalIF":0.0,"publicationDate":"2017-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89354597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sotiris Nousias, F. Chadebecq, Jonas Pichat, P. Keane, S. Ourselin, C. Bergeles
We propose a method for geometric calibration of multifocus plenoptic cameras using raw images. Multi-focus plenoptic cameras feature several types of micro-lenses spatially aligned in front of the camera sensor to generate micro-images at different magnifications. This multi-lens arrangement provides computational-photography benefits but complicates calibration. Our methodology achieves the detection of the type of micro-lenses, the retrieval of their spatial arrangement, and the estimation of intrinsic and extrinsic camera parameters therefore fully characterising this specialised camera class. Motivated from classic pinhole camera calibration, our algorithm operates on a checker-board’s corners, retrieved by a custom microimage corner detector. This approach enables the introduction of a reprojection error that is used in a minimisation framework. Our algorithm compares favourably to the state-of-the-art, as demonstrated by controlled and freehand experiments, making it a first step towards accurate 3D reconstruction and Structure-from-Motion.
{"title":"Corner-Based Geometric Calibration of Multi-focus Plenoptic Cameras","authors":"Sotiris Nousias, F. Chadebecq, Jonas Pichat, P. Keane, S. Ourselin, C. Bergeles","doi":"10.1109/ICCV.2017.109","DOIUrl":"https://doi.org/10.1109/ICCV.2017.109","url":null,"abstract":"We propose a method for geometric calibration of multifocus plenoptic cameras using raw images. Multi-focus plenoptic cameras feature several types of micro-lenses spatially aligned in front of the camera sensor to generate micro-images at different magnifications. This multi-lens arrangement provides computational-photography benefits but complicates calibration. Our methodology achieves the detection of the type of micro-lenses, the retrieval of their spatial arrangement, and the estimation of intrinsic and extrinsic camera parameters therefore fully characterising this specialised camera class. Motivated from classic pinhole camera calibration, our algorithm operates on a checker-board’s corners, retrieved by a custom microimage corner detector. This approach enables the introduction of a reprojection error that is used in a minimisation framework. Our algorithm compares favourably to the state-of-the-art, as demonstrated by controlled and freehand experiments, making it a first step towards accurate 3D reconstruction and Structure-from-Motion.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"957-965"},"PeriodicalIF":0.0,"publicationDate":"2017-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89027106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Depth sensors open up possibilities of dealing with the human action recognition problem by providing 3D human skeleton data and depth images of the scene. Analysis of human actions based on 3D skeleton data has become popular recently, due to its robustness and view-invariant representation. However, the skeleton alone is insufficient to distinguish actions which involve human-object interactions. In this paper, we propose a deep model which efficiently models human-object interactions and intra-class variations under viewpoint changes. First, a human body-part model is introduced to transfer the depth appearances of body-parts to a shared view-invariant space. Second, an end-to-end learning framework is proposed which is able to effectively combine the view-invariant body-part representation from skeletal and depth images, and learn the relations between the human body-parts and the environmental objects, the interactions between different human body-parts, and the temporal structure of human actions. We have evaluated the performance of our proposed model against 15 existing techniques on two large benchmark human action recognition datasets including NTU RGB+D and UWA3DII. The Experimental results show that our technique provides a significant improvement over state-of-the-art methods.
{"title":"Learning Action Recognition Model from Depth and Skeleton Videos","authors":"H. Rahmani, Bennamoun","doi":"10.1109/ICCV.2017.621","DOIUrl":"https://doi.org/10.1109/ICCV.2017.621","url":null,"abstract":"Depth sensors open up possibilities of dealing with the human action recognition problem by providing 3D human skeleton data and depth images of the scene. Analysis of human actions based on 3D skeleton data has become popular recently, due to its robustness and view-invariant representation. However, the skeleton alone is insufficient to distinguish actions which involve human-object interactions. In this paper, we propose a deep model which efficiently models human-object interactions and intra-class variations under viewpoint changes. First, a human body-part model is introduced to transfer the depth appearances of body-parts to a shared view-invariant space. Second, an end-to-end learning framework is proposed which is able to effectively combine the view-invariant body-part representation from skeletal and depth images, and learn the relations between the human body-parts and the environmental objects, the interactions between different human body-parts, and the temporal structure of human actions. We have evaluated the performance of our proposed model against 15 existing techniques on two large benchmark human action recognition datasets including NTU RGB+D and UWA3DII. The Experimental results show that our technique provides a significant improvement over state-of-the-art methods.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"9 1","pages":"5833-5842"},"PeriodicalIF":0.0,"publicationDate":"2017-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80713334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：