Human Detection Using Oriented Histograms of Flow and Appearance

Abstract

International audienceDetecting humans in films and videos is a challenging problem owing to the motion of the subjects, the camera and the background and to variations in pose, appearance, clothing, illumination and background clutter. We develop a detector for standing and moving people in videos with possibly moving cameras and backgrounds, testing several different motion coding schemes and showing empirically that orientated histograms of differential optical flow give the best overall performance. These motion-based descriptors are combined with our Histogram of Oriented Gradient appearance descriptors. The resulting detector is tested on several databases including a challenging test set taken from feature films and containing wide ranges of pose, motion and background variations, including moving cameras and backgrounds. We validate our results on two challenging test sets containing more than 4400 human examples. The combined detector reduces the false alarm rate by a factor of 10 relative to the best appearance-based detector, for example giving false alarm rates of 1 per 20,000 windows tested at 8% miss rate on our Test Set 1

Hollywood 3D: What are the Best 3D Features for Action Recognition?

“…Some of the most popular descriptors have been based on the gradient of the appearance information (Schuldt et al 2004;Laptev and Perez 2007), spatio-temporal extensions to SIFT and SURF descriptors (Scovanner et al 2007;Willems et al 2008) and 2D motion information (Dalal et al 2006;Messing et al 2009). However, there has been little previous work on feature descriptors including depth information (which is generally encoded directly at the holistic level, with the aid of user masks).…”

Accurate Human Detection by Appearance and Motion

“…Recently, there are also many motion based detectors [8]- [10], [29]. They are suitable for detecting human from video.…”

“…This method can get acceptable detection result in outdoor scene. [9], [10] also use optical flow. But instead of using flow directly, they extract characteristic feature from optical flow field.…”

“…The motion of human is different from the motion caused by other objects. Some detectors [8]- [10] are constructed by using the motion information. The combination of appearance based detector and motion based detector can detect the standing people and moving people efficiently from videos [10].…”

“…Some detectors [8]- [10] are constructed by using the motion information. The combination of appearance based detector and motion based detector can detect the standing people and moving people efficiently from videos [10]. Up to now, the computation complexity is still the bottleneck for many applications.…”