In: Paparoditis N., Pierrot-Deseilligny M.. Mallet C.. Tournaire O. (Eds). IAPRS. Vol. XXXVIII. Part ЗА - Saint-Mandé, France. September 1-3, 2010 
4. CONCLUSIONS 
The presented new approach for detecting and tracking people 
from aerial image sequences shows very promising first results. 
In addition, the achievements interpreting the trajectories 
demonstrate the potential of event detection. Several further 
developments and investigations are of interest: Haar-like 
features and AdaBoost classification (Sinai et al., 2010) is 
planned to be used in the future to improve the object detection 
component. Besides detection also tracking can be improved: 
although the algorithm can handle situations of a person being 
missed in a single frame, it fails completely when it happens in 
two or more consecutive frames. This drawback cannot be 
dissolved with the proposed optical-flow algorithm. Bridging 
more than one image would allow to construct longer 
trajectories, whose completeness increases significantly as the 
currently derived results. The trajectory interpretation module is 
exemplarily shown by two different events: obviously, the 
modeling of further scenarios is aimed to get a more overall 
monitoring of possible occurring events. The automatic 
detection of predefined events using statistical methods, similar 
to (Hongeng et al., 2004), is intended to be accomplished in the 
near future. In addition, a backward-loop is strived to be 
integrated in the system: results derived from the interpretation 
of the trajectories could be integrated in the strategies to 
improve the tracking model. Obviously, the dependent 
interpretation module will benefit afterwards from more reliable 
tracking results. 
REFERENCES 
Breitenstein, M., Grabner, H., van Gool, L., 2009. Hunting 
Nessie - Real-Time Abnormality Detection from Webcams. 
Proceedings International Conference on Computer Vision, 
pp. 1243-1250. 
Davis, L., Philomin, C., Duraiswami, R., 2000. Tracking 
Humans from a Moving Platform. Proceedings International 
Conference on Pattern Recognition, pp. 171-178. 
Helbing, D., Farkas, I.J., Molnar, P., Vicsek, T., 2002. 
Simulation of Pedestrian Crowds in Normal and Evacuation 
Situations. In: Schreckenberg, M„ Sharma, S. D. (eds.), 
Pedestrian and Evacuation Dynamics, Springer, pp. 21-58. 
Helbing, D., Molnar, P., 1995. Social Force Model for 
Pedestrian Dynamics. Physical Review E 51(5), pp. 4282-4286. 
Hinz, S., 2009. Density and Motion Estimation of People in 
Crowded Environments Based on Aerial Image Sequences. In: 
International Archives of Photogrammetry, Remote Sensing and 
Spatial Information Sciences 38(l-4-7/W5), on CD. 
Hongeng, S., Nevada, R., Bremond. F., 2004. Video-based 
Event Recognition: Activity Representation and Probabilistic 
Recognition Methods. Computer Vision and Image 
Understanding 96(2), pp. 129-162. 
Hu, W., Tan, T., Wang, L., Maybank, S., 2004. A Survey on 
Visual Surveillance of Object Motion and Behaviors. IEEE 
Transactions on Systems, Man and Cybernetics 34(3), pp. 334- 
352. 
Kang, J.. Cohen, I., Medioni, G., 2003. Continuous Tracking 
Within and Across Camera Streams. Proceedings Conference 
on Computer Vision and Pattern Recognition, pp. 267-272. 
Kurz. F., Mtiller, R., Stephani, M., Reinartz, P., Schröder, M., 
2007. Calibration of a Wide-angle Digital Camera System for 
Near Real-time Scenarios. In: International Archives of 
Photogrammetty, Remote Sensing and Spatial Information 
Sciences 36( 1 /W51), on CD. 
McKenna, S.J., Jabri, S., Duric, Z., Rosenfeld, A., Wechsler, 
H., 2000. Tracking Groups of People. Computer Vision and 
Image Understanding 80( 1). pp. 42-56. 
Medioni, G., Cohen, I.. Bremond, F., Hongeng, S., Nevada, R., 
2001. Event Detection and Analysis from Video Streams. IEEE 
Transactions on Pattern Analysis and Machine Intelligence 
23(8), pp.873-889. 
Mehran. R., Oyama, A., Shah, M., 2009. Abnormal Crowd 
Behavior Detection Using Social Force Model. Proceedings 
International Conference on Computer Vision and Pattern 
Recognition, pp. 935-942. 
Moeslund, T.B., Granum, E., 2001. A Survey of Computer 
Vision-based Human Motion Capture. Computer Vision and 
Image Understanding 81, pp. 231 -268. 
Nillius, P„ Sullivan, J., Carlsson. S., 2006. Multi-Target 
Tracking - Linking Identities Using Bayesian Network 
Inference. Proceedings Conference on Computer Vision and 
Pattern Recognition, pp. 2187-2194. 
Rodriguez, M., Ali, S., Kanade, T., 2009. Tracking in 
Unstructured Crowded Scenes. Proceedings International 
Conference on Computer Vision, pp. 1389-1396. 
Rohr, K. 1994. Towards Model-Based Recognition of Human 
Movements in Image Sequences. CVGIP: Image Understanding 
59(1), 94-115. 
Rosales, R., Sclaroff, S., 1999. 3D Trajectory Recovery for 
Tracking Multiple Objects and Trajectory Guided Recognition 
of Actions. Proceedings Conference Computer Vision and 
Pattern Recognition, pp. 117-123. 
Scovanner, P., Tappen, M., 2009. Learning Pedestrian 
Dynamics from the Real World. Proceedings International 
Conference on Computer Vision, pp. 381-388. 
Smal, L, Loog, M., Niessen, W., Meijering, E., 2010. 
Quantitative Comparison of Spot Detection Methods in 
Fluorescence Microscopy. IEEE Transactions on Medical 
Imaging 29(2), pp. 282-301. 
Yu, T., Wu, Y., 2004. Collaborative Tracking of Multiple 
Targets. Proceedings Conference Computer Vision and Pattern 
Recognition, pp. 834-841. 
Zhan, B., Monekosso, D. N., Remagnino, P., Velastin S. A., Xu 
L., 2008. Crowd Analysis: A Survey. Machine Vision and 
Applications 19(5-6), pp. 345-357. 
Zhao, T., Nevada, R., 2004. Tracking Multiple Humans in 
Complex Situations. IEEE Transactions on Pattern Analysis 
and Machine Intelligence 26(9), pp. 1208-1221. 
Zhao, T., Nevatia, R., Wu, N., 2008. Segmentation and 
Tracking of Multiple Humans in Crowded Environments. IEEE 
Transactions on Pattern Analysis and Machine Intelligence 
30(7), pp. 1198-1211. 
214