Dataset
in 'rawPixelPointPair.csv' columns are: image coordinate: halfH_x [:,0] halfH_y [:,1] H_x [:,2] H_y [:,3] pixel coordinate: halfH_u [:,5].astype(np.int64).tolist() halfH_v [:,6].astype(np.int64).tolist() H_u=(H_x+imageW//2).astype(np.int64).tolist() H_v=(H_y+imageH//2).astype(np.int64).tolist() MatchingQuaility: [:,9].astype(np.int64) For use, please cite:[1] Jiang, Y., and Bai, Y. (2020a). “Estimation of Construction Site Elevations Using Drone-Based Orthoimagery and Deep Learning.” Journal of Construction Engineering and Management, 146(8), 04020086, https://doi.org/10.1061/(ASCE)CO.1943-7862.0001869.[2] Jiang, Y., and Bai, Y. (2020b). “Determination of Construction Site Elevations Using Drone Technology.” Construction Research Congress 2020, American Society of Civil Engineers, Reston, VA, 296–305.[3] Jiang, Y., and Bai, Y. (2021). “Low–High Orthoimage Pairs-Based 3D Reconstruction for Elevation Determination Using Drone.” Journal of Construction Engineering and Management, 147(9), 04021097, https://doi.org/10.1061/(ASCE)CO.1943-7862.0002067.[4] Jiang, Y., Bai, Y., and Han, S. (2020). “Determining Ground Elevations Covered by Vegetation on Construction Sites Using Drone-Based Orthoimage and Convolutional Neural Network.” Journal of Computing in Civil Engineering, 34(6), 04020049, https://doi.org/10.1061/(ASCE)CP.1943-5487.0000930.[5] Han, S., Jiang, Y., and Bai, Y. (2022). “Fast-PGMED: Fast and Dense Elevation Determination for Earthwork Using Drone and Deep Learning.” Journal of Construction Engineering and Management, 148(4), 04022008, https://doi.org/10.1061/(ASCE)CO.1943-7862.0002256.
The automatic stitching of overlapped 2D images is much easier than the merging of 3D point clouds. Once two adjacent stations’ orthoimages are stitched, the stitching parameters can also be applied to merge and align elevation maps, see details in "Automated Ortho-image and Elevation-map Stitching" or https://www.yuhanjiang.com/research/DT /PGMED/Stitching
The automatic stitching of overlapped 2D images is much easier than the merging of 3D point clouds. Once two adjacent stations’ orthoimages are stitched, the stitching parameters can also be applied to merge and align elevation maps, see details in "Automated Ortho-image and Elevation-map Stitching" or https://www.yuhanjiang.com/research/DT /PGMED/Stitching
Development of a Pavement Evaluation Tool Using Google Earth Imagery and Deep Learning
@article{doi:10.1061/JPEODX.0000282,author = {Yuhan Jiang and Sisi Han and Yong Bai },title = {Development of a Pavement Evaluation Tool Using Aerial Imagery and Deep Learning},journal = {Journal of Transportation Engineering, Part B: Pavements},volume = {147},number = {3},pages = {04021027},year = {2021},doi = {10.1061/JPEODX.0000282}
URL = {https://ascelibrary.org/doi/abs/10.1061/JPEODX.0000282}For use, please cite: [1] Jiang, Y., Han, S., and Bai, Y. (2021). “Development of a Pavement Evaluation Tool Using Aerial Imagery and Deep Learning.” Journal of Transportation Engineering, Part B: Pavements, 147(3), 04021027, https://doi.org/10.1061/JPEODX.0000282.[2] Jiang, Y., Bai, Y., and Han, S. (2020). “Determining Ground Elevations Covered by Vegetation on Construction Sites Using Drone-Based Orthoimage and Convolutional Neural Network.” Journal of Computing in Civil Engineering, 34(6), 04020049, https://doi.org/10.1061/(ASCE)CP.1943-5487.0000930.[3] Jiang, Y., Han, S., and Bai, Y. (2021). “Building and Infrastructure Defect Detection and Visualization Using Drone and Deep Learning Technologies." ASCE Journal of Performance of Constructed Facilities, DOI: 10.1061/(ASCE)CF.1943-5509.0001652. [in press]
@article{doi:10.1061/JPEODX.0000282,author = {Yuhan Jiang and Sisi Han and Yong Bai },title = {Development of a Pavement Evaluation Tool Using Aerial Imagery and Deep Learning},journal = {Journal of Transportation Engineering, Part B: Pavements},volume = {147},number = {3},pages = {04021027},year = {2021},doi = {10.1061/JPEODX.0000282}
URL = {https://ascelibrary.org/doi/abs/10.1061/JPEODX.0000282}For use, please cite: [1] Jiang, Y., Han, S., and Bai, Y. (2021). “Development of a Pavement Evaluation Tool Using Aerial Imagery and Deep Learning.” Journal of Transportation Engineering, Part B: Pavements, 147(3), 04021027, https://doi.org/10.1061/JPEODX.0000282.[2] Jiang, Y., Bai, Y., and Han, S. (2020). “Determining Ground Elevations Covered by Vegetation on Construction Sites Using Drone-Based Orthoimage and Convolutional Neural Network.” Journal of Computing in Civil Engineering, 34(6), 04020049, https://doi.org/10.1061/(ASCE)CP.1943-5487.0000930.[3] Jiang, Y., Han, S., and Bai, Y. (2021). “Building and Infrastructure Defect Detection and Visualization Using Drone and Deep Learning Technologies." ASCE Journal of Performance of Constructed Facilities, DOI: 10.1061/(ASCE)CF.1943-5509.0001652. [in press]
In Label_imagespixel value=26: Pile of waste concrete pixel value=0: Non-concreteFor use, please cite: [1] Jiang, Y., Han, S., and Bai, Y. (2021). “Development of a Pavement Evaluation Tool Using Aerial Imagery and Deep Learning.” Journal of Transportation Engineering, Part B: Pavements, 147(3), 04021027, https://doi.org/10.1061/JPEODX.0000282.[2] Jiang, Y., Bai, Y., and Han, S. (2020). “Determining Ground Elevations Covered by Vegetation on Construction Sites Using Drone-Based Orthoimage and Convolutional Neural Network.” Journal of Computing in Civil Engineering, 34(6), 04020049, https://doi.org/10.1061/(ASCE)CP.1943-5487.0000930.[3] Jiang, Y., Han, S., and Bai, Y. (2021). “Building and Infrastructure Defect Detection and Visualization Using Drone and Deep Learning Technologies." ASCE Journal of Performance of Constructed Facilities, DOI: 10.1061/(ASCE)CF.1943-5509.0001652. [in press]
Image version/ Point cloud version [Link]In Label.csvpixel value=1: Waste concrete pixel value=0: Non-concreteFor use, please cite: [1] Jiang, Y., Han, S., and Bai, Y. (2021). “Development of a Pavement Evaluation Tool Using Aerial Imagery and Deep Learning.” Journal of Transportation Engineering, Part B: Pavements, 147(3), 04021027, https://doi.org/10.1061/JPEODX.0000282.[2] Jiang, Y., Bai, Y., and Han, S. (2020). “Determining Ground Elevations Covered by Vegetation on Construction Sites Using Drone-Based Orthoimage and Convolutional Neural Network.” Journal of Computing in Civil Engineering, 34(6), 04020049, https://doi.org/10.1061/(ASCE)CP.1943-5487.0000930.[3] Jiang, Y., Han, S., and Bai, Y. (2021). “Building and Infrastructure Defect Detection and Visualization Using Drone and Deep Learning Technologies." ASCE Journal of Performance of Constructed Facilities, DOI: 10.1061/(ASCE)CF.1943-5509.0001652. [in press]
Image version/ Point cloud version TBDIn Label.csvpixel value=1: Jointpixel value=0: Non-jointFor use, please cite: [1] Jiang, Y., Han, S., and Bai, Y. (2021). “Development of a Pavement Evaluation Tool Using Aerial Imagery and Deep Learning.” Journal of Transportation Engineering, Part B: Pavements, 147(3), 04021027, https://doi.org/10.1061/JPEODX.0000282.[2] Jiang, Y., Bai, Y., and Han, S. (2020). “Determining Ground Elevations Covered by Vegetation on Construction Sites Using Drone-Based Orthoimage and Convolutional Neural Network.” Journal of Computing in Civil Engineering, 34(6), 04020049, https://doi.org/10.1061/(ASCE)CP.1943-5487.0000930.[3] Jiang, Y., Han, S., and Bai, Y. (2021). “Building and Infrastructure Defect Detection and Visualization Using Drone and Deep Learning Technologies." ASCE Journal of Performance of Constructed Facilities, DOI: 10.1061/(ASCE)CF.1943-5509.0001652. [in press]
Image version/ Point cloud version TBDIn M00Label.csvpixel value=6: windowpixel value=0: Non-windowFree access on https://www.yuhanjiang.com/dataset
Testing Dataset: contains four facade images and labels.
For use, please cite: [1] Jiang, Y., Han, S., and Bai, Y. (2021). “Development of a Pavement Evaluation Tool Using Aerial Imagery and Deep Learning.” Journal of Transportation Engineering, Part B: Pavements, 147(3), 04021027, https://doi.org/10.1061/JPEODX.0000282.[2] Jiang, Y., Bai, Y., and Han, S. (2020). “Determining Ground Elevations Covered by Vegetation on Construction Sites Using Drone-Based Orthoimage and Convolutional Neural Network.” Journal of Computing in Civil Engineering, 34(6), 04020049, https://doi.org/10.1061/(ASCE)CP.1943-5487.0000930.[3] Jiang, Y., Han, S., and Bai, Y. (2021). “Building and Infrastructure Defect Detection and Visualization Using Drone and Deep Learning Technologies." ASCE Journal of Performance of Constructed Facilities, DOI: 10.1061/(ASCE)CF.1943-5509.0001652. [in press]
Testing Dataset: contains four facade images and labels.
For use, please cite: [1] Jiang, Y., Han, S., and Bai, Y. (2021). “Development of a Pavement Evaluation Tool Using Aerial Imagery and Deep Learning.” Journal of Transportation Engineering, Part B: Pavements, 147(3), 04021027, https://doi.org/10.1061/JPEODX.0000282.[2] Jiang, Y., Bai, Y., and Han, S. (2020). “Determining Ground Elevations Covered by Vegetation on Construction Sites Using Drone-Based Orthoimage and Convolutional Neural Network.” Journal of Computing in Civil Engineering, 34(6), 04020049, https://doi.org/10.1061/(ASCE)CP.1943-5487.0000930.[3] Jiang, Y., Han, S., and Bai, Y. (2021). “Building and Infrastructure Defect Detection and Visualization Using Drone and Deep Learning Technologies." ASCE Journal of Performance of Constructed Facilities, DOI: 10.1061/(ASCE)CF.1943-5509.0001652. [in press]
For use, please cite: [1] Jiang, Y., Han, S., and Bai, Y. (2021). “Development of a Pavement Evaluation Tool Using Aerial Imagery and Deep Learning.” Journal of Transportation Engineering, Part B: Pavements, 147(3), 04021027, https://doi.org/10.1061/JPEODX.0000282.[2] Han, S.; Chung, I.-H.; Jiang, Y.; Uwakweh, B. PCIer: Pavement Condition Evaluation Using Aerial Imagery and Deep Learning. Geographies 2023, 3, x. https://doi.org/10.3390/xxxxx