Full Record

New Search | Similar Records

Author
Title General Object Detection Using Superpixel Preprocessing
URL
Publication Date
Discipline/Department Computer Vision
University/Publisher Linköping University
Abstract The objective of this master’s thesis work is to evaluate the potential benefit of a superpixel preprocessing step for general object detection in a traffic environment. The various effects of different superpixel parameters on object detection performance, as well as the benefit of including depth information when generating the superpixels are investigated. In this work, three superpixel algorithms are implemented and compared, including a proposal for an improved version of the popular Spectral Linear Iterative Clustering superpixel algorithm (SLIC). The proposed improved algorithm utilises a coarse-to-fine approach which outperforms the original SLIC for high-resolution images. An object detection algorithm is also implemented and evaluated. The algorithm makes use of depth information obtained by a stereo camera to extract superpixels corresponding to foreground objects in the image. Hierarchical clustering is then applied, with the segments formed by the clustered superpixels indicating potential objects in the input image. The object detection algorithm managed to detect on average 58% of the objects present in the chosen dataset. It performed especially well for detecting pedestrians or other objects close to the car. Altering the density distribution of the superpixels in the image yielded an increase in detection rate, and could be achieved both with or without utilising depth information. It was also shown that the use of superpixels greatly reduces the amount of computations needed for the algorithm, indicating that a real-time implementation is feasible.
Subjects/Keywords superpixels; SLIC; coarse-to-fine; segmentation; general object detection; cityscapes; traffic; image processing; clustering; Computer Vision and Robotics (Autonomous Systems); Datorseende och robotik (autonoma system)
Language en
Country of Publication se
Record ID oai:DiVA.org:liu-140874
Repository diva
Date Indexed 2020-01-03

Sample Search Hits | Sample Images | Cited Works

…of this master’s thesis work is to evaluate the potential benefit of using a superpixel preprocessing step for general object detection in a traffic environment. The various effects of different superpixel parameters on the object detection

…images is proposed by Q. Xingming and W. Wei in [23]. The achieved segmentations are of good quality, although the algorithm does not run in real-time. Kootstra et al. propose a real-time general object detection algorithm in [13]. The…

…x28;right) contains less holes (dark blue) caused by invalid disparity values. 3.3 The Algorithm The goal of the object detection algorithm is to cluster together superpixels which correspond to general objects and create a…

…plane. In general this is 2 In practice, when having approximately 4000 points, good results are obtained for dividing the Z-axis into around 100 intervals. 28 3 Object Detection true for most intervals containing points close to the camera. The…

…viii 4.2.2 Evaluation Implementation . 4.2.3 Quantitative Results . . . . . 4.2.4 Segmentation Speed Analysis 4.3 Object Detection . . . . . . . . . . . . 4.3.1 Error Measures . . . . . . . . 4.3.2 Evaluation Results . . . . . . 4.3.3 Algorithm…

…5.2 Results for Object Detection . . . . . . . . . . . . . 5.2.1 The Error Measures . . . . . . . . . . . . . . 5.2.2 Increasing the Number of Superpixels . . . 5.2.3 The Effect of Altering the Distance Measure 5.2.4 Using the Median Disparity…

…5.3.2 Object Detection

…takes an image obtained from a car-mounted stereo camera pair and attempts to find potential objects. This process can mainly be divided into two steps: 1. Perform a superpixel segmentation of the image. 2. Run an object detection algorithm on the…

.