Published on Tue Jun 04 2019

4-D Scene Alignment in Surveillance Video

Robert Wagner, Daniel Crispell, Patrick Feeney, Joe Mundy

An automatic camera calibration process that provides a mechanism to reason about the spatial proximity between objects at different times. Unlike some previous methods, the people do not need to be tracked nor do the head and feet need be explicitly detected.

0
0
0
Abstract

Designing robust activity detectors for fixed camera surveillance video requires knowledge of the 3-D scene. This paper presents an automatic camera calibration process that provides a mechanism to reason about the spatial proximity between objects at different times. It combines a CNN-based camera pose estimator with a vertical scale provided by pedestrian observations to establish the 4-D scene geometry. Unlike some previous methods, the people do not need to be tracked nor do the head and feet need to be explicitly detected. It is robust to individual height variations and camera parameter estimation errors.

Wed Jan 15 2020
Computer Vision
Moving Objects Detection with a Moving Camera: A Comprehensive Review
Survey identifies and categorizes the different existing methods found in the literature. Methods are grouped according to eight different approaches.
0
0
0
Mon Dec 09 2019
Computer Vision
Car Pose in Context: Accurate Pose Estimation with Ground Plane Constraints
0
0
0
Thu Nov 19 2015
Computer Vision
Structured Depth Prediction in Challenging Monocular Video Sequences
In this paper, we tackle the problem of estimating the depth of a scene from a monocular video sequence. We handle challenging scenarios, such as non-translational camera motion and dynamic scenes, where traditional structure from motion and motion stereo methods do not apply.
0
0
0
Wed Jun 02 2021
Computer Vision
Online and Real-Time Tracking in a Surveillance Scenario
This paper presents an approach for tracking in a surveillance scenario. Typical aspects for this scenario are a 24/7 operation with a static camera above the height of a human with many objects or people. The Multiple Object Tracking Benchmark 20 reflects this scenario best.
3
0
0
Wed Apr 04 2018
Computer Vision
A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation
We present a unifying framework to solve several computer vision problems with event cameras. The main idea of our framework is to find the point trajectories on the image plane that are best aligned with the event data by maximizing an objective function.
0
0
0
Tue Mar 11 2008
Computer Vision
Spatio-activity based object detection
SAMMI lightweight object detection method has a high level of accuracy and robustness. Background modeling is based on DCT grotesquecoefficients provided by cameras. Foreground detection uses similarity in temporal characteristics of adjacent blocks of pixels.
0
0
0