Exploiting projective geometry for view-invariant monocular human motion analysis in man-made environments

Rogez, Grégory; Orrite, Carlos; Guerrero, J. J.; Torr, Philip H. S.

doi:10.1016/j.cviu.2013.12.012

Cited by 10 publications

(10 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Projective transformation, or homography, is an established approach for correcting perspective distortion [13], but this traditional approach requires the vanishing point to be manually specified. Rogez et al [14,3] used vertical scene lines to estimate the vanishing point and localize the reconstructed poses based on the vanishing point, but their approach still requires manual determination of which lines are vertical. Our homography step is similar to Rogez et al's, except we determine the vanishing point based on the altitude and angle of the camera.…”

Section: Perspective Correctionmentioning

confidence: 99%

See 1 more Smart Citation

Human Pose and Path Estimation from Aerial Video Using Dynamic Classifier Selection

2018

View full text Add to dashboard Cite

Background / introduction-We consider the problem of estimating human pose and trajectory by an aerial robot with a monocular camera in near real time. We present a preliminary solution whose distinguishing feature is a dynamic classifier selection architecture.Methods-In our solution, each video frame is corrected for perspective using projective transformation. Then, two alternative feature sets are used: (i) Histogram of Oriented Gradients (HOG) of the silhouette, (ii) Convolutional Neural Network (CNN) features of the RGB image. The features (HOG or CNN) are classified using a dynamic classifier. A class is defined as a pose-viewpoint pair, and a total of 64 classes are defined to represent a forward walking and turning gait sequence.Results-Our solution provides three main advantages: (i) Classification is efficient due to dynamic selection (4-class vs. 64-class classification). (ii) Classification errors are confined to neighbors of the true viewpoints. (iii) The robust temporal relationship between poses is used to resolve the left-right ambiguities of human silhouettes.Conclusions-Experiments conducted on both frontoparallel videos and aerial videos confirm our solution can achieve accurate pose and trajectory estimation for both scenarios. We found using HOG features provides higher accuracy than using CNN features. For example, applying the HOG-based variant of our scheme to the "walking on a figure 8-shaped path" dataset (1652 frames) achieved estimation accuracies of 99.6% for viewpoints and 96.2% for number of poses.

show abstract

Section: Perspective Correctionmentioning

confidence: 99%

“…The perspective correction module compensates for perspective distortion in aerial videos using a projective transformation technique similar to [1,2,3]. Instead of one homography matrix, pre-annotated homography matrices are used for different levels of distortion caused by different camera elevation angles.…”

Section: Introductionmentioning

confidence: 99%

Human Pose and Path Estimation from Aerial Video Using Dynamic Classifier Selection

2018

View full text Add to dashboard Cite

show abstract

“…In this study, we restrict ourselves to monocular vision with single images of the streets. Different cues of depth can be present in monocular vision such as textures, shadows, defocus [40], parallel lines [41] producing in a projective geometry the presence of vanishing point on the horizon line, repetition of similar objects at different distances from the camera.…”

Section: Impact Of Vegetation On Monocular Depth Cuesmentioning

confidence: 99%

Toward a Computer Vision Perspective on the Visual Impact of Vegetation in Symmetries of Urban Environments

et al. 2018

View full text Add to dashboard Cite

Rapid urbanization is a worldwide critical environmental challenge. With this urban migration soaring, we need to live far more efficiently than we currently do by incorporating the natural world in new and innovative ways. There are a lot of researches on ecological, architectural or aesthetic points of view to address this issue. We present a novel approach to assess the visual impact of vegetation in urban street pedestrian view with the assistance of computer vision metrics. We statistically evaluate the correlations of the amount of vegetation with objective computer vision traits such as Fourier domain, color histogram, and estimated depth from monocular view. We show that increasing vegetation in urban street views breaks the orthogonal symmetries of urban blocks, enriches the color space with fractal-like symmetries and decreases the cues of projective geometry in depth. These uncovered statistical facts are applied to predict the requested amount of vegetation to make urban street views appear like natural images. Interestingly, these amounts are found in accordance with the ecosystemic approach for urban planning. Also, the study opens new questions for the understanding of the link between geometry and depth perception.

show abstract

“…Existing work on the same dataset either employs clustering algorithms with GPU optimisation [25], or focusses on motion analysis by matching trained silhouette models [28]. We differ significantly from these previous works: we developed an accurate tracking framework in which we can employ a highly accurate pedestrian detector on these challenging images, and thus perform much better than existing methods.…”

Section: Related Workmentioning

confidence: 99%

Pedestrian Detection and Tracking in Challenging Surveillance Videos

Beeck

Goedemé

2016

Communications in Computer and Information Science

View full text Add to dashboard Cite

In this chapter we propose a novel approach for real-time robust pedestrian tracking in surveillance images. Typical surveillance images are challenging to analyse since the overall image quality is low (e.g. low resolution and high compression). Furthermore often birds-eye viewpoint wide-angle lenses are used to achieve maximum coverage with a minimal amount of cameras. These specific viewpoints make it unfeasible to directly apply existing pedestrian detection techniques. Moreover, real-time processing speeds are required. To overcome these problems we introduce a pedestrian detection and tracking framework which exploits and integrates these scene constraints to achieve high accuracy results. We performed extensive experiments on publically available challenging real-life video sequences concerning both speed and accuracy. Our approach achieves excellent accuracy results while still meeting the stringent real-time demands needed for these surveillance applications, using only a single-core CPU implementation.

show abstract

Exploiting projective geometry for view-invariant monocular human motion analysis in man-made environments

Cited by 10 publications

References 65 publications

Human Pose and Path Estimation from Aerial Video Using Dynamic Classifier Selection

Human Pose and Path Estimation from Aerial Video Using Dynamic Classifier Selection

Toward a Computer Vision Perspective on the Visual Impact of Vegetation in Symmetries of Urban Environments

Pedestrian Detection and Tracking in Challenging Surveillance Videos

Contact Info

Product

Resources

About