Automotive DNN-Based Object Detection in the Presence of Lens Obstruction and Video Compression
Recent advances in sensing, processing, machine learning, and communication technologies are accelerating assisted and automated functions development for commercial vehicles. Environmental perception sensor data streams are processed to generate a correct and complete situational awareness. It is o...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10900335/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850235939279863808 |
|---|---|
| author | Gabriele Baris Boda Li Pak Hung Chan Carlo Alberto Avizzano Valentina Donzella |
| author_facet | Gabriele Baris Boda Li Pak Hung Chan Carlo Alberto Avizzano Valentina Donzella |
| author_sort | Gabriele Baris |
| collection | DOAJ |
| description | Recent advances in sensing, processing, machine learning, and communication technologies are accelerating assisted and automated functions development for commercial vehicles. Environmental perception sensor data streams are processed to generate a correct and complete situational awareness. It is of utmost importance to assess the robustness of the sensor data pipeline, particularly in the case of data degradation in a noisy and variable environment. Sensor data reduction and compression techniques are key for higher levels of driving automation, as there is an expectation that traditional automotive vehicle wired networks will not be able to support the needed sensor datarates (i.e. more than 10 perception sensors, including cameras, LiDARs, and RADARs, generating tens of Gb/s of data). This work proposes for the first time to consider video compression for camera data transmission on vehicle wired networks in the presence of highly noisy data, e.g. partially obstructed camera field of view. The effects are discussed in terms of machine learning vehicle detection accuracy drop, and also visualising how detection performance spatially varies on the frames using the recently introduced metric, the Spatial Recall Index (SRI). The presented parametric obstruction noise model is generated to emulate real-world patterns, whereas compression is based on the well-established AVC/H.264. While Deep Neural Networks’ (DNNs’) performance is stable with lossy compression (up to 70:1) of ‘ideal’ data, when noise is added there is a significant accuracy degradation, in the range of a 7%-90% decrease. The proposed compression and noise tuning of the DNN training improves the performance up to 35%, enhancing the noise and compression robustness of the system. However, in the presence of compression combined with extreme levels of noise (i.e. more than 80% of pixels affected), DNN performance significantly degrades, up to a 90% decrease, even with re-training. This issue needs to be carefully considered in the design phase of perception and communication networks used to transmit sensor data. |
| format | Article |
| id | doaj-art-32006ca273124bb5a2b066722a8037ed |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-32006ca273124bb5a2b066722a8037ed2025-08-20T02:02:06ZengIEEEIEEE Access2169-35362025-01-0113365753658910.1109/ACCESS.2025.354477310900335Automotive DNN-Based Object Detection in the Presence of Lens Obstruction and Video CompressionGabriele Baris0Boda Li1https://orcid.org/0000-0002-3051-0875Pak Hung Chan2https://orcid.org/0000-0003-1705-5430Carlo Alberto Avizzano3https://orcid.org/0000-0001-5802-541XValentina Donzella4https://orcid.org/0000-0002-3408-6135WMG, University of Warwick, Coventry, U.K.WMG, University of Warwick, Coventry, U.K.WMG, University of Warwick, Coventry, U.K.Institute of Mechanical Intelligence, Sant' Anna School of Advanced Studies, Pisa, ItalyWMG, University of Warwick, Coventry, U.K.Recent advances in sensing, processing, machine learning, and communication technologies are accelerating assisted and automated functions development for commercial vehicles. Environmental perception sensor data streams are processed to generate a correct and complete situational awareness. It is of utmost importance to assess the robustness of the sensor data pipeline, particularly in the case of data degradation in a noisy and variable environment. Sensor data reduction and compression techniques are key for higher levels of driving automation, as there is an expectation that traditional automotive vehicle wired networks will not be able to support the needed sensor datarates (i.e. more than 10 perception sensors, including cameras, LiDARs, and RADARs, generating tens of Gb/s of data). This work proposes for the first time to consider video compression for camera data transmission on vehicle wired networks in the presence of highly noisy data, e.g. partially obstructed camera field of view. The effects are discussed in terms of machine learning vehicle detection accuracy drop, and also visualising how detection performance spatially varies on the frames using the recently introduced metric, the Spatial Recall Index (SRI). The presented parametric obstruction noise model is generated to emulate real-world patterns, whereas compression is based on the well-established AVC/H.264. While Deep Neural Networks’ (DNNs’) performance is stable with lossy compression (up to 70:1) of ‘ideal’ data, when noise is added there is a significant accuracy degradation, in the range of a 7%-90% decrease. The proposed compression and noise tuning of the DNN training improves the performance up to 35%, enhancing the noise and compression robustness of the system. However, in the presence of compression combined with extreme levels of noise (i.e. more than 80% of pixels affected), DNN performance significantly degrades, up to a 90% decrease, even with re-training. This issue needs to be carefully considered in the design phase of perception and communication networks used to transmit sensor data.https://ieeexplore.ieee.org/document/10900335/Automated vehiclesobject detectionnoisecompressiondeep neural networks |
| spellingShingle | Gabriele Baris Boda Li Pak Hung Chan Carlo Alberto Avizzano Valentina Donzella Automotive DNN-Based Object Detection in the Presence of Lens Obstruction and Video Compression IEEE Access Automated vehicles object detection noise compression deep neural networks |
| title | Automotive DNN-Based Object Detection in the Presence of Lens Obstruction and Video Compression |
| title_full | Automotive DNN-Based Object Detection in the Presence of Lens Obstruction and Video Compression |
| title_fullStr | Automotive DNN-Based Object Detection in the Presence of Lens Obstruction and Video Compression |
| title_full_unstemmed | Automotive DNN-Based Object Detection in the Presence of Lens Obstruction and Video Compression |
| title_short | Automotive DNN-Based Object Detection in the Presence of Lens Obstruction and Video Compression |
| title_sort | automotive dnn based object detection in the presence of lens obstruction and video compression |
| topic | Automated vehicles object detection noise compression deep neural networks |
| url | https://ieeexplore.ieee.org/document/10900335/ |
| work_keys_str_mv | AT gabrielebaris automotivednnbasedobjectdetectioninthepresenceoflensobstructionandvideocompression AT bodali automotivednnbasedobjectdetectioninthepresenceoflensobstructionandvideocompression AT pakhungchan automotivednnbasedobjectdetectioninthepresenceoflensobstructionandvideocompression AT carloalbertoavizzano automotivednnbasedobjectdetectioninthepresenceoflensobstructionandvideocompression AT valentinadonzella automotivednnbasedobjectdetectioninthepresenceoflensobstructionandvideocompression |