@inproceedings{AgrawalElger2021, author = {Agrawal, Shiva and Elger, Gordon}, title = {Concept of infrastructure based environment perception for IN2Lab test field for automated driving}, booktitle = {2021 IEEE International Smart Cities Conference (ISC2)}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-6654-4919-9}, issn = {2687-8860}, doi = {https://doi.org/10.1109/ISC253183.2021.9562894}, year = {2021}, language = {en} } @inproceedings{AgrawalSongDoychevaetal.2023, author = {Agrawal, Shiva and Song, Rui and Doycheva, Kristina and Knoll, Alois and Elger, Gordon}, title = {Intelligent Roadside Infrastructure for Connected Mobility}, booktitle = {Smart Cities, Green Technologies, and Intelligent Transport Systems: 11th International Conference, SMARTGREENS 2022 and 8th International Conference, VEHITS 2022: Revised Selected Papers}, editor = {Klein, Cornel and Jarke, Matthias and Ploeg, Jeroen and Helfert, Markus and Berns, Karsten and Gusikhin, Oleg}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-37470-8}, issn = {1865-0937}, doi = {https://doi.org/10.1007/978-3-031-37470-8_6}, pages = {134 -- 157}, year = {2023}, language = {en} } @inproceedings{AgrawalBhanderiAmanagietal.2023, author = {Agrawal, Shiva and Bhanderi, Savankumar and Amanagi, Sumit and Doycheva, Kristina and Elger, Gordon}, title = {Instance Segmentation and Detection of Children to Safeguard Vulnerable Traffic User by Infrastructure}, booktitle = {Proceedings of the 9th International Conference on Vehicle Technology and Intelligent Transport Systems}, editor = {Vinel, Alexey and Ploeg, Jeroen and Berns, Karsten and Gusikhin, Oleg}, publisher = {SciTePress}, address = {Set{\´u}bal}, isbn = {978-989-758-652-1}, issn = {2184-495X}, doi = {https://doi.org/10.5220/0011825400003479}, pages = {206 -- 214}, year = {2023}, abstract = {Cameras mounted on intelligent roadside infrastructure units and vehicles can detect humans on the road using state-of-the-art perception algorithms, but these algorithms are presently not trained to distinguish between human and adult. However, this is a crucial requirement from a safety perspective because a child may not follow all the traffic rules, particularly while crossing the road. Moreover, a child may stop or may start playing on the road. In such situations, the separation of a child from an adult is necessary. The work in this paper targets to solve this problem by applying a transfer-learning-based neural network approach to classify child and adult separately in camera images. The described work is comprised of image data collection, data annotation, transfer learning-based model development, and evaluation. For the work, Mask-RCNN (region-based convolutional neural network) with different backbone architectures and two different baselines are investigated and the perception precision of the architectures after transfer-learning is compared. The results reveal that the best performing trained model is able to detect and classify children and adults separately in different road scenarios with segmentation mask AP (average precision) of 85\% and bounding box AP of 92\%.}, language = {en} } @article{AgrawalBhanderiElger2025, author = {Agrawal, Shiva and Bhanderi, Savankumar and Elger, Gordon}, title = {Infra-3DRC-FusionNet: Deep Fusion of Roadside Mounted RGB Mono Camera and Three-Dimensional Automotive Radar for Traffic User Detection}, volume = {25}, pages = {3422}, journal = {Sensors}, number = {11}, publisher = {MDPI}, address = {Basel}, issn = {1424-8220}, doi = {https://doi.org/10.3390/s25113422}, year = {2025}, abstract = {Mono RGB cameras and automotive radar sensors provide a complementary information set that makes them excellent candidates for sensor data fusion to obtain robust traffic user detection. This has been widely used in the vehicle domain and recently introduced in roadside-mounted smart infrastructure-based road user detection. However, the performance of the most commonly used late fusion methods often degrades when the camera fails to detect road users in adverse environmental conditions. The solution is to fuse the data using deep neural networks at the early stage of the fusion pipeline to use the complete data provided by both sensors. Research has been carried out in this area, but is limited to vehicle-based sensor setups. Hence, this work proposes a novel deep neural network to jointly fuse RGB mono-camera images and 3D automotive radar point cloud data to obtain enhanced traffic user detection for the roadside-mounted smart infrastructure setup. Projected radar points are first used to generate anchors in image regions with a high likelihood of road users, including areas not visible to the camera. These anchors guide the prediction of 2D bounding boxes, object categories, and confidence scores. Valid detections are then used to segment radar points by instance, and the results are post-processed to produce final road user detections in the ground plane. The trained model is evaluated for different light and weather conditions using ground truth data from a lidar sensor. It provides a precision of 92\%, recall of 78\%, and F1-score of 85\%. The proposed deep fusion methodology has 33\%, 6\%, and 21\% absolute improvement in precision, recall, and F1-score, respectively, compared to object-level spatial fusion output.}, language = {en} } @article{AgrawalBhanderiElger2024, author = {Agrawal, Shiva and Bhanderi, Savankumar and Elger, Gordon}, title = {Semi-Automatic Annotation of 3D Radar and Camera for Smart Infrastructure-Based Perception}, volume = {12}, journal = {IEEE Access}, publisher = {IEEE}, address = {New York}, issn = {2169-3536}, doi = {https://doi.org/10.1109/ACCESS.2024.3373310}, pages = {34325 -- 34341}, year = {2024}, abstract = {Environment perception using camera, radar, and/or lidar sensors has significantly improved in the last few years because of deep learning-based methods. However, a large group of these methods fall into the category of supervised learning, which requires a considerable amount of annotated data. Due to uncertainties in multi-sensor data, automating the data labeling process is extremely challenging; hence, it is performed manually to a large extent. Even though full automation of such a process is difficult, semiautomation can be a significant step to ease this process. However, the available work in this regard is still very limited; hence, in this paper, a novel semi-automatic annotation methodology is developed for labeling RGB camera images and 3D automotive radar point cloud data using a smart infrastructure-based sensor setup. This paper also describes a new method for 3D radar background subtraction to remove clutter and a new object category, GROUP, for radar-based object detection for closely located vulnerable road users. To validate the work, a dataset named INFRA-3DRC is created using this methodology, where 75\% of the labels are automatically generated. In addition, a radar cluster classifier and an image classifier are developed, trained, and tested on this dataset, achieving accuracy of 98.26\% and 94.86\%, respectively. The dataset and Python scripts are available at https://fraunhoferivi.github.io/INFRA-3DRC-Dataset/.}, language = {en} } @article{AgrawalBhanderiDoychevaetal.2023, author = {Agrawal, Shiva and Bhanderi, Savankumar and Doycheva, Kristina and Elger, Gordon}, title = {Static multi-target-based auto-calibration of RGB cameras, 3D Radar, and 3D Lidar sensors}, volume = {23}, journal = {IEEE Sensors Journal}, number = {18}, publisher = {IEEE}, address = {Piscataway}, issn = {1530-437X}, doi = {https://doi.org/10.1109/JSEN.2023.3300957}, pages = {21493 -- 21505}, year = {2023}, language = {en} } @inproceedings{AgrawalSongKohlietal.2022, author = {Agrawal, Shiva and Song, Rui and Kohli, Akhil and Korb, Andreas and Andre, Maximilian and Holzinger, Erik and Elger, Gordon}, title = {Concept of Smart Infrastructure for Connected Vehicle Assist and Traffic Flow Optimization}, booktitle = {Proceedings of the 8th International Conference on Vehicle Technology and Intelligent Transport Systems}, editor = {Ploeg, Jeroen and Helfert, Markus and Berns, Karsten and Gusikhin, Oleg}, publisher = {SciTePress}, address = {Set{\´u}bal}, isbn = {978-989-758-573-9}, issn = {2184-495X}, doi = {https://doi.org/10.5220/0011068800003191}, pages = {360 -- 367}, year = {2022}, abstract = {The smart infrastructure units can play a vital role to develop smart cities of the future and in assisting automated vehicles on the road by providing extended perception and timely warnings to avoid accidents. This paper focuses on the development of such an infrastructure unit, that is specifically designed for a pedestrian crossing junction. It can control traffic lights at the junction by real-time environment perception through its sensors and can optimize the flow of vehicles and passing vulnerable road users (VRUs). Moreover, it can assist on-road vehicles by providing real-time information and critical warnings via a v2x module. This paper further describes different use-cases of the work, all major hardware components involved in the development of smart infrastructure unit, referred to as an edge, different sensor fusion approaches using the camera, radar, and lidar mounted on the edge for environment perception, various modes of communication including v2x, system design}, language = {en} } @article{BhanderiAgrawalElger2025, author = {Bhanderi, Savankumar and Agrawal, Shiva and Elger, Gordon}, title = {Deep segmentation of 3+1D radar point cloud for real-time roadside traffic user detection}, volume = {15}, pages = {38489}, journal = {Scientific Reports}, publisher = {Springer Nature}, address = {London}, issn = {2045-2322}, doi = {https://doi.org/10.1038/s41598-025-23019-6}, year = {2025}, abstract = {Smart cities rely on intelligent infrastructure to enhance road safety, optimize traffic flow, and enable vehicle-to-infrastructure (V2I) communication. A key component of such infrastructure is an efficient and real-time perception system that accurately detects diverse traffic participants. Among various sensing modalities, automotive radar is one of the best choices due to its robust performance in adverse weather and low-light conditions. However, due to low spatial resolution, traditional clustering-based approaches for radar object detection often struggle with vulnerable road user detection and nearby object separation. Hence, this paper proposes a deep learning-based D radar point cloud clustering methodology tailored for smart infrastructure-based perception applications. This approach first performs semantic segmentation of the radar point cloud, followed by instance segmentation to generate well-formed clusters with class labels using a deep neural network. It also detects single-point objects that conventional methods often miss. The described approach is developed and experimented using a smart infrastructure-based sensor setup and it performs segmentation of the point cloud in real-time. Experimental results demonstrate 95.35\% F1-macro score for semantic segmentation and 91.03\% mean average precision (mAP) at an intersection over union (IoU) threshold of 0.5 for instance segmentation. Further, the complete pipeline operates at 43.61 frames per second with a memory requirement of less than 0.7 MB on the edge device (Nvidia Jetson AGX Orin).}, language = {en} } @unpublished{BhanderiAgrawalElger2025, author = {Bhanderi, Savankumar and Agrawal, Shiva and Elger, Gordon}, title = {Deep Segmentation of 3+1D Radar Point Cloud for Real-Time Roadside Traffic User Detection}, titleParent = {Research Square}, publisher = {Research Square}, address = {Durham}, doi = {https://doi.org/10.21203/rs.3.rs-7222130/v1}, year = {2025}, abstract = {Smart cities rely on intelligent infrastructure to enhance road safety, optimize traffic flow, and enable vehicle-to-infrastructure (V2I) communication. A key component of such infrastructure is an efficient and real-time perception system that accurately detects diverse traffic participants. Among various sensing modalities, automotive radar is one of the best choices due to its robust performance in adverse weather and low-light conditions. However, due to low spatial resolution, traditional clustering-based approaches for radar object detection often struggle with vulnerable road user detection and nearby object separation. Hence, this paper proposes a deep learning-based 3+1D radar point cloud clustering methodology tailored for smart infrastructure-based perception applications. This approach first performs semantic segmentation of the radar point cloud, followed by instance segmentation to generate well-formed clusters with class labels using a deep neural network. It also detects single-point objects that conventional methods often miss. The described approach is developed and experimented using a smart infrastructure-based sensor setup and it performs segmentation of the point cloud in real-time. Experimental results demonstrate 95.35\% F1-macro score for semantic segmentation and 91.03\% mean average precision (mAP) at an intersection over union (IoU) threshold of 0.5 for instance segmentation. Further, the complete pipeline operates at 43.61 frames per second with a memory requirement of less than 0.7 MB on the edge device (Nvidia Jetson AGX Orin).}, language = {en} }