SVCL Motion Classification

Sidewalk02... Scene Description - [html] [pdf]
Congestion Level Experiments Oblique Angle Still				Experiment Accuracy
				Martin NN = 56% Nearest-neighbor classifier using Martin distance. State KL NN = 54% Nearest-neighbor classifier using state KL divergence State KL SVM = 57% SVM classifier using state KL kernel Image KL NN = 54% Nearest-neighbor classifier using image KL divergence Image KL SVM = 55% SVM classifier using image KL kernel
Description In this experiment, we attempt to discriminate between three congestion levels of pedsetrian traffic using still clips at an oblique angle Location: Bridge above walkway in Marshall College, UC, San Diego.	Clips: High Flow divx mov mp4 divx 1 mov (h.264) 1 mp4 (mpeg4) 1	Clips: Medium Flow divx mov mp4 divx 1 2 3 4 5 6 mov (h.264) 1 2 3 4 5 6 mp4 (mpeg4) 1 2 3 4 5 6	Clips: Low Flow divx mov mp4 divx 1 2 3 4 mov (h.264) 1 2 3 4 mp4 (mpeg4) 1 2 3 4

Front Angle Still				Experiment Accuracy

Description In this experiment, we attempt to discriminate between three congestion levels of pedsetrian traffic using still clips at a front angle Location: walkway in Marshall College, UC, San Diego.	Clips: High Flow divx mov mp4 divx 1 mov (h.264) 1 mp4 (mpeg4) 1	Clips: Medium Flow divx mov mp4 divx 1 2 3 mov (h.264) 1 2 3 mp4 (mpeg4) 1 2 3	Clips: Low Flow divx mov mp4 divx 1 2 mov (h.264) 1 2 mp4 (mpeg4) 1 2

Side Angle Still				Experiment Accuracy

Description In this experiment, we attempt to discriminate between three congestion levels of pedsetrian traffic using still clips at a side angle Location: walkway in Marshall College, UC, San Diego.	Clips: Medium Flow divx mov mp4 divx 1 2 3 mov (h.264) 1 2 3 mp4 (mpeg4) 1 2 3	Clips: Low Flow divx mov mp4 divx 1 2 3 4 mov (h.264) 1 2 3 4 mp4 (mpeg4) 1 2 3 4

Front Angle Pan				Experiment Accuracy

Description Nothing yet.	Clips: Low Flow divx mov mp4 divx 1 mov (h.264) 1 mp4 (mpeg4) 1