Stereovision-based mobile mapping system 
    
Normalized images 
  
i Dense matching using 
emm the semi-global block 
matching algorithm 
  
  
  
   
X. 
  
Depth map 
  
  
J i 
  
  
Automated detection, classification and mapping 
  
of road signs 
  
l 
  
  
  
  
Templates Region of interest 
  
  
i J 
  
     
| 
Type 3D position 
  
  
  
  
Figure 2. Input and output data for the automated detection, classification and 3D mapping of road signs 
3. DEVELOPED ALGORITHMS AND 
3.1 Automated detection of road signs 
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
  
37 
SOFTWARE MODULES 
The input to the detection process consists of the left TL 
The presented approach which is based on stereo images and normalized image and the corresponding depth map for each us 
depth maps was implemented in Matlab with several algorithms stereo image pair (see Figure 4). Since no permanent road signs pri 
and software modules. They cover the whole workflow from the are expected to occur in the lower third of the normalized cl: 
automated detection and classification through to the mapping image, this region is colored black. As the hue und saturation CO 
of road signs (see Figure 3) and are explained below. components are relatively insensitive to the varying lighting be 
conditions, which are typical to vision-based mobile mapping, cai 
ET the RGB normalized image is transformed into the HSV color 
Normalized image | | Depth map INPUT ; ; Th 
space. Afterwards, the depth map is used to restrict the 
subsequent search space in the imagery by applying a co 
Transformation into predefined distance range interval. To enable the detection of als 
HSV Color Space road signs on an adjacent lane, a base-depth ratio from 0.06 to thı 
7 x ; ; 0.25 was chosen. In addition, with a high image acquisition C 
| Reduction fo predefined distance range interval | frequency, the same road sign can be detected and classified thi 
p E TRE ; 
redundantly. The segmentation of red, blue and yellow color ob 
| Color segmentation | - - : cl: 
segments is carried out using thresholds for the hue and 
; saturation components, which were determined empirically Th 
Evaluation of color segments based : f diff t . . For bi 1 
(criteria for dimensions) ; ased on images from different measuring campaigns. For blue di 
1 Generation of DETECTION segments, the hue values have to be between 0.52 and 0.72 and (e. 
Shape determination using planar segments the saturation range is from 0.20 to 0.80. Pixels featuring a hue CO 
roundness and fill factor value between 0.04 and 0.19 as well as a saturation value which CO 
i is higher than 0.50 and smaller than 0.98 are covering yellow his 
Computation of segments. If the area of the color segment corresponds to co 
standardized dimensions distance-related criteria, its shape is described by the two rec 
Y features roundness and fill factor: co 
Computation of wi 
detection indicator roundness = 4-x- segment area (1) de 
segment circumference? > 
Predefined ; d ; segment area va 
A CLASSIFICATION fill factor = — — — Eme Q) : 
minimum bounding rectangle area y 
im 
Determination of 3D position MAPPING The extents of a segment must match the standardized road sign @ 
dimensions within a certain tolerance. Again, the dense depth W 
OUTPUT maps are used in determining the metric heights and widths of ob 
segments in object space. The depth maps are also utilized in co 
the detection of planar segments. These are regions with similar the 
Figure 3. Developed algorithms for the automated detection, depth values. The ratio between the area of the planar segment we 
classification and 3D mapping of chromatic road signs in the color segment (intersection of Figure 4f and 4j) and the Th 
(gray fields: operations exploiting the disparity and 
depth information respectively) 
full area of the color segment (Figure 4f) serves as detection 
indicator which is used to assess the detection process. 
60