Abandoned Object Detection in
Video-Surveillance: Survey and Comparison
This page provides additional material and software
for the paper:
Abandoned
Object Detection in Video-Surveillance: Survey and Comparison
[link]
Elena
Luna, J. SanMiguel, Diego Ortego
and José M. Martínez
Published in Sensors December 2018
Abstract During the
last years, abandoned object detection emerged as a hot topic in the
video-surveillance community. As a consequence, a myriad of systems have been
proposed for automatic monitoring of public and private places, while
addressing several challenges affecting detection performance. Due to the
complexity of these systems, researchers often address independently their
stages such as foreground segmentation, stationary object detection and
abandonment validation. Despite the improvement achieved for each stage, the
advances are rarely applied to the full pipeline and therefore, the impact on
the overall system performance is not studied. In this paper, we formalize the
framework employed by systems for abandoned object detection and provide an
extensive review of state-of-the-art approaches. We also conduct experimental
comparisons of existing approaches over a heterogeneous dataset presenting
various challenges such as illumination changes, shadows and high densities of
moving objects. For such comparison, we build a multi-configuration system
allowing to select a range of alternatives for each stage, which is made
available online to the research community. The experimental results identify
the most effective configurations and highlight design choices favoring
robustness to errors. We conclude the paper by discussing open research
challenges arising from the experimental compariso
Requirements: Ubuntu 16.04 Opencv 3.4.1 compiled for C++ Qt Creator 5.7.0 (optional) THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. DUE TO LACK OF RESOURCES, WE CANNOT AFFORD TO SUPPORT ANY ISSUES YOU MAY FIND WHEN RUNNING, INTEGRATING OR DEVELOPING USING THE PROVIDED SOURCE CODE.