Research Projects


[Cross-View Action Recognition]

 

 

Abstract:

This paper concerns recognition of human actions under view changes. We explore self-similarities of action sequences over time and observe the striking stability of such measures across views. Building upon this key observation we develop an action descriptor that captures the structure of temporal similarities and dissimilarities within an action sequence. Despite this descriptor not being strictly view-invariant, we provide intuition and experimental validation demonstrating the high stability of self-similarities under view changes. Self-similarity descriptors are also shown stable under action variations within a class as well as discriminative for action recognition. Interestingly, self-similarities computed from different image features possess similar properties and can be used in a complementary fashion. Our method is simple and requires neither structure recovery nor multi-view correspondence estimation. Instead, it relies on weak geometric cues captured by self-similarities and combines them with machine learning for efficient cross-view action recognition. The method is validated on three public datasets, it has similar or superior performance compared to related methods and it performs well even in extreme conditions such as when recognizing actions from top views while using side views for training only.

 

Related Publication:

- View-Independent Action Recognition from Temporal Self-Similarities
        Imran Junejo, Emilie Dexter, Ivan Laptev, Patrick Perez
        IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (TPAMI),
        March, 2010

- Cross-View Action Recognition from Temporal Self-Similarities

       Imran N. Junejo, Emilie Dexter, Ivan Laptev, and Patrick Perez

        Proc. The 10th European Conference on Computer Vision (ECCV), 2008.  new!

 

[GPS Coordinate Estimation using Shadow Trajectories]

 

 

Abstract

Using only shadow trajectories of stationary objects in a scene, we demonstrate that using a set of six or more photographs are sufficient to accurately calibrate the camera. Moreover, we present a novel application where, using only three points from the shadow trajectory of the objects, one can accurately determine the geo-location of the camera, up to a longitude ambiguity, and also the date of image acquisition without using any GPS or other special instruments. We refer to this as "geo-temporal localization". We consider possible cases where ambiguities can be removed if additional information is available. Our method does not require any knowledge of the date or the time when the pictures are taken, and geo-temporal information is recovered directly from the images. We demonstrate the accuracy of our technique for both steps of calibration and geo-temporal localization using synthetic and real data.

 

Related Publications

- GPS Coordinates Estimation and Camera Calibration from Solar Shadows for Computer Forensics
        Imran Junejo, Hassan Foroosh
        Elsevier Computer Vision and Image Understanding (CVIU),
        accepted (in press), 2010.

- Estimating Geo-Temporal Location of Stationary Cameras Using Shadow Trajectories

        Imran N. Junejo and Hassan Foroosh

        Proc. The 10th European Conference on Computer Vision (ECCV), 2008. new!

- Using Solar Shadow Trajectories for Camera Calibration

        Imran N. Junejo, and Hassan Foroosh

        15th IEEE International Conference on Image Processing (ICIP), 2008. new!

 

[Camera Calibration from Pedestrians on Uneven Terrain]

 

Abstract

A calibrated camera is essential for computer vision systems. The prime reason being that such a camera acts as an angle measuring device. Once the camera is calibrated, applications like 3D reconstruction or metrology or other applications requiring real world information from the video sequences can be envisioned. Motivated by this, we address the problem of calibrating multiple cameras, with an overlapping field of view (FoV) observing pedestrians in a scene walking on an uneven terrain. This problem of calibration on an uneven terrain has so far not been addressed in the vision community. We automatically estimate vertical and horizontal vanishing points by observing pedestrians in each camera and use the corresponding vanishing points to estimate the infinite homography existing between the different cameras. This homography provides constraints on intrinsic (or interior) camera parameters while also enabling us to estimate the extrinsic (or exterior) camera parameters.We test the proposed method on real as well as synthetic data, in addition to motion capture dataset and compare our results with the state of the art.

 

Related Publications

- Using Pedestrians Walking on Uneven Terrains for Camera Calibration
       Imran Junejo
         Springer Journal of Machine Vision and Applications (MVA),
         DOI: 10.1007/s00138-009-0210-2, 2009

- Camera Calibration for Uneven Terrains by Observing Pedestrians
        Imran N. Junejo
        Nineteenth Springer International Conference on Pattern Recognition (ICPR), 2008.
 

[Euclidean Path Modeling for Video Surveillance]

 

 

Abstract

We address the issue of Euclidean path modeling in a single camera for activity monitoring in a multi-camera video surveillance system. The method consists of a path building training phase and a testing phase. During the unsupervised training phase, after auto-calibrating a camera and thereafter metric rectifying the input trajectories, a weighted graph is constructed with trajectories represented by the nodes, and weights determined by a similarity measure. Normalized-cuts are recursively used to partition the graph into prototype paths. Each path, consisting of a partitioned group of trajectories, is represented by a path envelope and an average trajectory. For every prototype path, features such as spatial proximity, motion characteristics, curvature, and absolute world velocity are then recovered directly in the rectified images or by registering to aerial views. During the testing phase, using our simple yet efficient similarity measures for these features, we seek a relation between the trajectories of an incoming sequence and the prototype path models to identify anomalous and unusual behaviors. Real-world pedestrian sequences are used to evaluate the steps, and demonstrate the practicality of the proposed approach.

 

Related Publications

- Euclidean Path Modeling for Video Surveillance

        Imran Junejo and Hassan Foroosh

        Elsevier Journal of Image and Vision Computing (IVC), 2007.(PDF)

- Trajectory Rectification and Path Modeling for Video Surveillance

        Imran N. Junejo, and Hassan Foroosh

        Eleventh IEEE International Conference on Computer Vision (ICCV), 2007

        [Acceptance Rate 23.5%]. (PDF)

- Multi Feature Path Modeling for Video Surveillance

        Imran N. Junejo, Omar Javed, Mubarak Shah,

        17th conference of the International Conference on Pattern Recognition (ICPR), 2004. (PDF)