Lists

Monday, May 30, 2022

Preprint on unconventional cameras for automotive applications

From arXiv.org --- You Li et al. write:

Autonomous vehicles rely on perception systems to understand their surroundings for further navigation missions. Cameras are essential for perception systems due to the advantages of object detection and recognition provided by modern computer vision algorithms, comparing to other sensors, such as LiDARs and radars. However, limited by its inherent imaging principle, a standard RGB camera may perform poorly in a variety of adverse scenarios, including but not limited to: low illumination, high contrast, bad weather such as fog/rain/snow, etc. Meanwhile, estimating the 3D information from the 2D image detection is generally more difficult when compared to LiDARs or radars. Several new sensing technologies have emerged in recent years to address the limitations of conventional RGB cameras. In this paper, we review the principles of four novel image sensors: infrared cameras, range-gated cameras, polarization cameras, and event cameras. Their comparative advantages, existing or potential applications, and corresponding data processing algorithms are all presented in a systematic manner. We expect that this study will assist practitioners in the autonomous driving society with new perspectives and insights.








11 comments:


  1. From my point of view, this is just one in a long string of B.S. papers that survey the literature in a general way and really say nothing new at all. Did I miss something here?

    Meanwhile, the IEEE Trans. Electron Devices special issue on solid-state image sensors has been published (June 2022) containing some excellent invited, open-acess papers on hardcore image sensor technology. Thanks Mike Guidash and IISS members for pulling this together!
    https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=16

    ReplyDelete
    Replies
    1. I'm counting only 13 open access papers out of more than 100 in this particular issue.

      Delete
    2. @funkster You're right - of the papers for the special issue, only 7 or 8 are open access, including the 2 that I co-authored. When I first looked at it, I was signed in to my Dartmouth account which "unlocks" all the papers, and I misinterpreted that, but when I signed in from outside Dartmouth, I see that far fewer papers are unlocked. i guess this is a good time to mention the benefits of IEEE membership! (But personally, I really hate all these paywalls and that is why all IISS papers are available to the public at large.)

      Delete
    3. Vladimir, why you censored my comment to Eric? I really want to know how he allows himself call my paper B.S.? It's a review paper. He publishes so many review papers. Please post my last comment and don't censor it.

      Delete
    4. @anonymous If I could edit out "B.S." I would, so sorry for hurting your feelings. But, I am still mourning the old ISW blog site created and curated by Vladimir. This site has now become more of a computer vision site, and image sensor technology is no longer the focus (But I am grateful to Atul for posting from time to time). Meanwhile, why do you write anonymously since you are obviously one of the 3 authors? And why don't you start your title with the words "Survey of"? This looks like a great topic for a book, but it is so broad to be ineffective at communicating the depth of history or insights into autonomous navigation in a few short pages. And, it certainly does not do much to discuss the underlying technical details, esp. for image sensors. It is kind of a very short undergraduate senior thesis. What is your plan for publishing this paper somewhere besides the no-peer-review ArXiv repository?

      Delete
  2. Hi Eric, thanks for the link. To me most of the papers seem to be open access, at least I have the green unlock symbol and could open the ones I tried (and I am not logged in). Maybe Atul could post links to a few, there are very interesting overview papers - for example "Overview of CMOS Global Shutter Pixels" https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9667125, "
    Angular Dependency of the Light Sensitivity" (by Albert) https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9758950 or "Evolution of Image Sensor Architectures With Stacked Device Technologies" https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9494712

    ReplyDelete
    Replies
    1. These papers appear to be locked to me...

      Delete
  3. thanks for sharing. And thanks to mr Fossum, his invention literally changed my life. I joined Micron in 2004 on DRAM, then switched on image sensor in 2005, first smartphones, then automotive (with a stint in DSLR); so much learning and fun through all the challenges. Thanks to mr Fossum.

    ReplyDelete
  4. It's a review, it helps to catch up the state of the art. For example, the PolarLITIS dataset looks interesting.

    ReplyDelete
  5. Thank you for pointing out the latest issue of IEEE Trans. Electron Devices. I see that many of these papers are behind a paywall. I will post summaries of papers from this issue over the coming days. Stay tuned!

    ReplyDelete
    Replies
    1. Very kind of you! Looking forward to them...

      Delete

All comments are moderated to avoid spam and personal attacks.