Dump Truck Recognition Based on SCPSR in Videos
Dump truck recognition plays an important role in the state-owned land surveillance system, which aims at fore-warning illegal construction. However, there is no special algorithm for dump truck recognition. In this paper, we explore a dump truck recognit
- PDF / 1,717,233 Bytes
- 9 Pages / 439.37 x 666.142 pts Page_size
- 65 Downloads / 165 Views
Abstract. Dump truck recognition plays an important role in the stateowned land surveillance system, which aims at fore-warning illegal construction. However, there is no special algorithm for dump truck recognition. In this paper, we explore a dump truck recognition algorithm combing structure components projection with spatial relationship (SCPSR). Instead of detecting dump truck directly as a whole, we propose a dump truck recognition algorithm based on foreground detection and components detection. An improved three frames difference method is used for foreground detection. Inspired by structure feature of dump truck components, we first locate the wheels by its valley feature on gray-scale image, and then search the candidate cab and hopper zones with the help of spatial relationship. Further, cab and hopper zones are determined by the components projection. Combining foreground detection with components detection method, the system is able to provide realtime and reliable vehicle supervision results. Experiments on real site videos demonstrate promising performance of the proposed algorithm. Keywords: Dump truck recognition · SCPSR · Valley feature ture components projection · Spatial relationship
1
· Struc-
Introduction
Protecting the state-owned land from encroachment has been the main responsibility of the regulatory department. At present, the main regulation methods include remote sensing [1,2], human inspection [3] and vehicle video monitoring [4]. However, there are some shortcomings in these methods, such as poor realtime, high cost and unavailable for the bumpy areas. The intelligent surveillance system will be a replaceable method to realize automation and saving labor. At present, there are few video analysis methods which aim at monitoring construction activities. Especially, because of various views and complex background [5], the existing front-view or rear-view methods mostly used in highway [6,7] are not suitable for the dump track detection. As dump truck can handle multiple activities, dump truck has been widely used in different stages of the project. In c Springer Nature Singapore Pte Ltd. 2016 T. Tan et al. (Eds.): CCPR 2016, Part II, CCIS 663, pp. 325–333, 2016. DOI: 10.1007/978-981-10-3005-5 27
326
W. Yang et al.
Fig. 1. The structure of the dump truck.
this case, dump truck detection is a key indicator for illegal construction on the state-owned land [8]. There is few literature involving dump truck detection, but the papers about vehicles detection on the road or highway can give us some ideas. Over the past two decades, many methods for vehicle detection in the context of traffic surveillance have been proposed [9–11]. All those methods can be roughly divided into two stages: foreground detection and target recognition [12]. In foreground detection stage, there are three popular methods: frame difference [13], background difference [14] and optical flow [15]. Robust detection algorithms such as Histogram of Oriented Gradients (HOG) [16,17] and Harr-like features [18] have been dev
Data Loading...
