Vehicle Counting in Video Sequences: An Incremental Subspace Learning Approach

Abstract

The counting of vehicles plays an important role in measuring the behavior patterns of traffic flow in cities, as streets and avenues can get crowded easily. To address this problem, some Intelligent Transport Systems (ITSs) have been implemented in order to count vehicles with already established video surveillance infrastructure. With this in mind, in this paper, we present an on-line learning methodology for counting vehicles in video sequences based on Incremental Principal Component Analysis (Incremental PCA). This incremental learning method allows us to identify the maximum variability (i.e., motion detection) between a previous block of frames and the actual one by using only the first projected eigenvector. Once the projected image is obtained, we apply dynamic thresholding to perform image binarization. Then, a series of post-processing steps are applied to enhance the binary image containing the objects in motion. Finally, we count the number of vehicles by implementing a virtual detection line in each of the road lanes. These lines determine the instants where the vehicles pass completely through them. Results show that our proposed methodology is able to count vehicles with 96.6% accuracy at 26 frames per second on average—dealing with both camera jitter and sudden illumination changes caused by the environment and the camera auto exposure.

Video-Based Vehicle Counting for Expressway: A Novel Approach Based on Vehicle Detection and Correlation-Matched Tracking Using Image Data from PTZ Cameras

“…Different from the single detection line method and the double detection line method, which only record the instantaneous changes of the vehicle motion, our counting method records the changes of vehicles in a period of time (within the region), which greatly improved the accuracy of counting. [31], and Rosas-Arias et al [27] applied image processing method such as updated background image, background subtraction, and Incremental PCA to detect vehicles. Meanwhile, vehicle tracking was not used for vehicle counting in the three methods mentioned in [2,27,31].…”

“…[31], and Rosas-Arias et al [27] applied image processing method such as updated background image, background subtraction, and Incremental PCA to detect vehicles. Meanwhile, vehicle tracking was not used for vehicle counting in the three methods mentioned in [2,27,31]. Moreover, Yang et al [32] adopted background subtraction method for vehicle detection and Kalman filter algorithm for vehicle tracking to achieve vehicle counting.…”

“…Considering the original approach for vehicle counting is based on virtual test lines [27], which is to set up virtual test lines on the road, we design an algorithm that can be applied to multi-vehicle counting, which simultaneously counts different categories of vehicles.…”

An Approach for Streaming Data Feature Extraction Based on Discrete Cosine Transform and Particle Swarm Optimization

“…The approach is based on IPCA, which employs SVD algorithm. Fujiwara [22] presented incremental dimensionality reduction algorithm based on IPCA for visualizing streaming multidimensional data. The presented approach uses SVD for computing eigenspace.…”

Measurement of Dynamic Responses from Large Structural Tests by Analyzing Non-Synchronized Videos

“…By taking videos or a series of images of structural experiments and employing computer vision techniques, the overall deformation of a specimen can be recorded. In addition, object tracking and image analysis techniques can be used to quantify the movement of certain points on the specimen [3,4], extract object motions [5], structural vibrations in real earthquake events [6], object identification and counting [7], and shape classification [8]. Optical measurement technique based on optical flight time is also used for object distance estimation and 3-D positioning [9] and is further applied for civil applications such as visually impaired aiding [10].…”