David Zhang

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2019-24

May 6, 2019

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2019/EECS-2019-24.pdf

On-the-road vehicle and pedestrian detection for self-driving cars thus far has been a combination of sonar, lidar, and cameras. For cameras, although object detection has improved dramatically in the last 20 years, common algorithms are best suited to handle static images and treat videos as a series of disjoint detections. Sequences across time can hold extra information allowing for improved detection performance as well as the added benefit of tracking objects through time. Thsi research doubles a standard fully convolutional network into a siamese architecture to handle consecutive frame inputs and adds a tracking module to assist in the prediction of frame to frame differences. The architecture is evaluated on both a standard dataset and a custom dataset to test its ability to handle more in-scene complexity.

Advisors: Trevor Darrell

---

BibTeX citation:

@mastersthesis{Zhang:EECS-2019-24,
    Author= {Zhang, David},
    Title= {Combined Detection and Tracking Impacts on Vehicle Specific Data},
    School= {EECS Department, University of California, Berkeley},
    Year= {2019},
    Month= {May},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2019/EECS-2019-24.html},
    Number= {UCB/EECS-2019-24},
    Abstract= {On-the-road vehicle and pedestrian detection for self-driving cars thus far has been a combination of sonar, lidar, and cameras. For cameras, although object detection has improved dramatically in the last 20 years,  common algorithms are best suited to handle static images and treat videos as a series of disjoint detections. Sequences across time can hold extra information allowing for improved detection performance as well as the added benefit of tracking objects through time. Thsi research doubles a standard fully convolutional network into a siamese architecture to handle consecutive frame inputs and adds a tracking module to assist in the prediction of frame to frame differences. The architecture is evaluated on both a standard dataset and a custom dataset to test its ability to handle more in-scene complexity.},
}

EndNote citation:

%0 Thesis
%A Zhang, David 
%T Combined Detection and Tracking Impacts on Vehicle Specific Data
%I EECS Department, University of California, Berkeley
%D 2019
%8 May 6
%@ UCB/EECS-2019-24
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2019/EECS-2019-24.html
%F Zhang:EECS-2019-24