Detection of Temporary Objects in Mobile Lidar Point Clouds Xinwei Fang Guorui Li Kourosh Khoshelham Sander Oude Elberink BACKGROUND  Mobile laser scanning provides an accurate recording of road environments useful for many applications;  Usually only permanent objects are of interest;  Temporary objects can hamper the analysis of permanent ones;  Example: change detection using multi-epoch data where temporary objects appear as (false) change signals. APPROACH  Temporary objects: Static Moving  Static temporary objects:  segmentation + classification based on shape features  Moving temporary objects:  segmentation + closest point analysis in two sensor data STATIC TEMPORARY OBJECTS  Classification based on shape features: Linear & short Linear & high Volumetric & high Planar Volumetric & short MOVING TEMPORARY OBJECTS  Detection based on closest point analysis with two sensor data Sensor 1 Sensor 2 METHODS 1. Ground removal 2. Connected-component segmentation 3. Static temporary objects:  feature extraction + classification 4. Moving temporary objects:  closest point analysis + classification GROUND REMOVAL  Plane-based segmentation  Ground = large & low segment CONNECTED COMPONENT SEGMENTATION  Points that are closer than a certain distance (e.g. 30 cm) belong to one connected component; FEATURE EXTRACTION  Shape features  Size (number of points)  Area on horizontal plane  Mean density  Height of the lowest point  Height  Contextual feature  Distance to trajectory  Eigen-based features  Anisotropy  Planarity  Sphericity  Linearity CLASSIFICATION  Ground truth for training and evaluation: manual labeling (115 samples)  Feature selection  Forward Selection (FS)  Backward Elimination (BE)  Classification  Linear Discrimnant Classifier (LDC)  Support Vector Machine (SVM) CLOSEST POINT ANALYSIS Static Moving Number Static objects Moving objects 45 24 EXPERIMENTS  Study area  Enschede, urban  Data  TopScan MLS  One strip: ~20 mio points RESULTS  Detection results for static temporary objects (test set): Classifier Completeness Correctness LDC - all features 0.90 0.86 LDC - FS (8 features) 0.90 0.79 LDC - BE (8 features) 0.95 0.91 SVM - all features 1.00 0.91 SVM - FS (9 features) 1.00 1.00 SVM - BE (11 features) 1.00 0.95 RESULTS  Classification results for the whole strip : 12 RESULTS  Detection results for moving objects:  Total 64 samples  4 false positives  6 false negatives Completeness Correctness Overall Accuracy Sensor 1 Sensor 2 Sensor1 + Sensor2 0.93 0.90 0.84 0.86 0.96 0.83 0.90 0.93 0.84 LIMITATIONS  Occlusion;  Overgrown and undergrown segments;  Shrunk or elongated shapes due to movement.  Variable shape and size of vehicles. CONCLUSIONS  Object-based approach: natural choice as we are dealing with objects not points;  Connected component segmentation of objects works well (but not perfect!);  Shape features are suitable for classification of static temporary objects; Accuracy > 90%.  Distance between closest points is a useful measure for detecting moving objects; Accuracy > 80%  Occlusion: objects seen by one sensor but not the other = problem for moving objects. 13 THANK YOU!