illumination assessment for vision based traffic
play

Illumination Assessment for Vision-Based Traffic Monitoring By - PowerPoint PPT Presentation

Illumination Assessment for Vision-Based Traffic Monitoring By SHRUTHI KOMAL GUDIPATI Outline Introduction PVS system design & concepts Assessing lighting Assessing contrast Assessing shadow presence Conclusion


  1. Illumination Assessment for Vision-Based Traffic Monitoring By SHRUTHI KOMAL GUDIPATI

  2. Outline  Introduction  PVS system design & concepts  Assessing lighting  Assessing contrast  Assessing shadow presence  Conclusion

  3. Introduction  Vision systems in traffic domain operates autonomously over varying environmental conditions  Uses different parameter values or algorithms depending on these conditions  Parameters depends on ambient conditions on camera images

  4. PVS system  Commercial real-time vision system for traffic monitoring that detects, tracks, and counts vehicles  Uses large volume of video data obtained from 25 different scenes  Switches between different parameter values and algorithms depending on scene illumination aspects

  5. Aspects of Scene illumination  Is the scene well-lit?  Is vehicle bodies visible?  In poorly lit scenes, Are only vehicle lights visible ?

  6. Aspects of Scene illumination 

  7. Aspects of Scene illumination

  8. Aspects of Scene Iillumination  Is the contrast sharp enough?  Ex:  Is visibility sufficient for reliable detection ?  Is visibility sufficient or too diminished ?  Fog, Dust or Snow

  9. Aspects of Scene illumination  Are vehicles in the scene casting shadows?

  10. PVS System Design  Processes frames at 30 Hz  Process images simultaneously up to 4 cameras  Compact and fits in 3U VME board

  11. 3U VME Board

  12. PVS system hardware  Two Texas Instruments TMS320C31 DSP chips  A Sensar pyramid chip  Custom ALU implemented using a Xilinx chip

  13. Operation principle  Maintains a reference image that contains the scene as it would appear if no vehicles were present  Each incoming frame is compared to the reference  Pixels where there are significant differences are grouped together into "fragments" by the detection algorithm  These fragments are grouped and tracked from frame to frame using a predictive filter

  14. One dimensional strip representation  Reduces the 2D image of each lane to a 1D "strip“  Integration operation that sums two pixel- wise measures across the portion of each image row that is spanned by the lane, resulting in a brightness and energy measurement for each row  Integration operation is performed by the ALU, which takes as input a bit-mask identifying each lane

  15. 2D -> 1D transformation

  16. Strip measurements  Two measurements, brightness and energy, are computed for each strip element y of each strip s  Brightness B(s,y) = Σ (pixels in Wy)  Energy E(s,y) = [Σ (absolute difference between every two adjacent pixels in W) ] / ااWyاا

  17. Reference strips  Brightness and Energy measurements gathered from a strip over time are used to construct a reference strip  For scenes in which traffic is flowing freely, reference strip can be constructed by IIR filtering  IIR filtering doesn’t work in stop-and-go or very crowded areas

  18. Reference strips  Strip element in reference image is updated  If 1 second has elapsed after the last time a significant dt (frame-to-frame difference) value was observed at that position  If 1 minute has elapsed since the last update

  19. Strip element classification  Classify each strip element on the current strip as background or non- background  Done by computing the brightness and energy difference measures  ΔB(y) = B(I,y) - B (R,y) - (o اا W(y) اا )  ΔE(y) = ا (E(I,y) - E(R,y ا

  20. Classification as Background or non- Background

  21. Strip element classification  Each strip element that is classified as non-background is further classified as "bright" or "dark“  Depends on whether its brightness is greater or less than the brightness of the corresponding reference strip element

  22. Illumination Assessment  All frames grabbed in a two-minute interval, all strip elements that both have been identified as non- background and have significant dt are used to update various statistical measures  Values of these measures are used to assess the lighting, contrast, and shadows

  23. Fragment Detection  Groups non-background strip elements into symbolic "vehicle fragments“  To prevent false positive vehicle detections, the system avoids detecting the illumination artifacts as vehicle fragments

  24. Fragment Detection  Uses three different detection techniques, depending on the nature of the scene illumination  Detection in well-lit scenes without vehicle shadows  Detection in well-lit scenes with vehicle shadows  Detection in poorly-lit scenes

  25. Fragment Detection Detection in well-lit scenes without vehicle shadows Scene as well-lit if the entire vehicle body is  Visible Scenes are termed poorly-lit if the only clearly-  visible vehicle components are the headlights or taillights

  26. Fragment Detection Detection in well-lit scenes with vehicle shadows  Well-lit scenes where vehicles are casting shadows, the detection process must be modified so that non-background strip elements due to shadows are not grouped into vehicle fragments  Uses stereo or motion cues to infer height

  27. Fragment Detection Detection in poorly-lit scenes  Where only vehicle lights are visible, fragment extraction via connected components is prone to false positives due to headlight reflections  Fragments are extracted by identifying compact bright regions of non-background strip elements around local brightness maxima

  28. Fragment tracking & grouping After the vehicle fragments have been extracted, they are passed to the Tracker module which tracks over time and groups them into objects

  29. Assessing lighting  Measures used for assessing whether the scene is well-lit, i.e. whether the entire body of most vehicles will be visible  Ndark + Nbright = total number of non- background pixels that were detected  Pdark = Ndark/(Ndark+Nbright)  If the scene is poorly-lit, the background image will be quite dark, and it will be difficult to detect any pixel with a dark surface color. Under this condition ndark will be small, and hence Pdark will be small

  30. Assessing contrast  Two typical causes of insufficient contrast -- fog or raindrops  Contrast can be measured using the energy difference measure ΔE(y)  In low-contrast scenes that occur during the day, vehicles will usually appear as objects darker than the haze, which often appears rather bright  In low-contrast scenes occurring at night, no dark regions will be detectable  Measure ΔEbright and ΔEdark

  31. Assessing shadow presence  Scenes that are well-lit can be decomposed into two sub-classes  Shadows Non - Shadows   Contrast of a "bright" portion of a vehicle against the road surface would be less than that of a "dark" portion

  32. Assessing shadow presence  Using k 4 = 1.2, this method has been found to work well  Sometimes, when there are very faint shadows, it does classify the scene as having no shadows  Fails when the background is not a road  For example, in some scenes a camera is looking at the road primarily from the side, and the vehicles occlude either objects (e.g. trees) or the sky as they move across the scene

  33. Illumination Assessment module  Three methods for assessing lighting, contrast, and shadows are applied sequentially

  34. Illumination Assessment module

  35. Conclusions  During Strip representation, transformation from 2D -> 1D is not clearly explained  In strip classification, the global offset “o” is mentioned to have been measured by a different process. The paper doesn’t mention/explain anything about the process  The paper mentions that the deployment results were satisfactory but it doesn’t provide any statistical data to support the claim

  36. References Wixson, L.B. , Hanna, K. , Mishra, D. , Improved  Illumination Assessment for Vision-Based Traffic Monitoring, VS98 (Image Processing for Visual Surveillance) Hanna, K. L. Wixso and D. Mishra , Illumination Assessment for  Vision-Based Traffic Monitoring, ICPR '96: Proceedings of the International Conference on Pattern Recognition Femer et al. 941 N.J. Ferrier, S.M. Rowe, A. Blake, "Real-Time  Traffic Monitoring," in Proceedings of the IEEE Workshop on Applications of Computer Vision, pages 81-88, 1994 Kilger 911 M. Kilger, "A Shadow Handler in a Video-based Real-  time Traffic Monitoring System", in Proceedings of the IEEE Workshop on Applications of Computer Vision, pages 11-18, 1992

  37. Questions ?

Recommend


More recommend