A configurable architecture for the generalized hough transform applied to the analysis of huge aerial images and to traffic sign detection

Abstract

Object recognition in huge image data sets or in live camera images at interactive frame rates is a very demanding task, especially within embedded systems. The recognition task includes the localization of a reference object and its rotation and scaling in a search image. The Generalized Hough Transform (GHT) is known as a powerful and robust technique to support this task by transforming the search image into a 4D parameter space. However, the GHT itself is very complex and demanding towards computational power and memory consumption. This paper presents a novel hardware architecture to perform a complete 4D GHT at interactive frame rates in an FPGA. The architecture is configurable in order to allow a trade-off between performance, accuracy and hardware usage. The proposed architecture has been implemented in a low-cost Zynq-7000 FPGA and successfully evaluated in two practical applications, namely groyne detection in aerial images and traffic sign detection

Automatic Extraction of Offshore Platforms in Single SAR Images Based on a Dual-Step-Modified Model

“…Any line in the plane is represented by a polar coordinate equation, which can be determined by two parameters: ρ and θ. For any point in the image space, the functional relationship is: ρ=x cosθ+y sinθ where θ∈[0,π], θ represents the angle between ρ and the positive x -axis, and ρ represents the distance from the point to the line [34,35,36]. If the abovementioned transformation is performed on n points located on the same straight line L , n points of the original image space correspondingly obtain n sinusoids in the parameter space, and the curves intersect at one point, indicating that the points are on the same line, as shown in Figure 3 [37].…”

Relative vectors clustering and temporal constraint based generalized Hough transform for high frame rate and ultra-low delay arbitrary shape detection

“…But their system can only process low resolution images (44 * 36 pixels). Another work was published by Gundolf Kiefer et al 1 . They proposed a configurable architecture to perform a 4D GHT to detect traffic signs at VGA size images.…”

“…In recent decades, machine vision, as a well-known and contactless inspection technology, has been deeply researched and widely applied in numerous fields. With the development of industrial automation, machine vision is becoming one of the key technologies for the next progression of factorial automation, such as sign detection 1 , object tracking 2 , object detection and high precise location 3 . Shape information, as a common geometric information, plays a crucial role in many industrial scenarios.…”