th0rnlin
  • NEW!
    NEW!  Connect Ideas Across Notes
    Save time and share insights. With Paragraph Citation, you can quote others’ work with source info built in. If someone cites your note, you’ll see a card showing where it’s used—bringing notes closer together.
    Got it
      • Create new note
      • Create a note from template
        • Sharing URL Link copied
        • /edit
        • View mode
          • Edit mode
          • View mode
          • Book mode
          • Slide mode
          Edit mode View mode Book mode Slide mode
        • Customize slides
        • Note Permission
        • Read
          • Only me
          • Signed-in users
          • Everyone
          Only me Signed-in users Everyone
        • Write
          • Only me
          • Signed-in users
          • Everyone
          Only me Signed-in users Everyone
        • Engagement control Commenting, Suggest edit, Emoji Reply
      • Invite by email
        Invitee

        This note has no invitees

      • Publish Note

        Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note No publishing access yet

        Your note will be visible on your profile and discoverable by anyone.
        Your note is now live.
        This note is visible on your profile and discoverable online.
        Everyone on the web can find and read all notes of this public team.

        Your account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

        Your team account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

        Explore these features while you wait
        Complete general settings
        Bookmark and like published notes
        Write a few more notes
        Complete general settings
        Write a few more notes
        See published notes
        Unpublish note
        Please check the box to agree to the Community Guidelines.
        View profile
      • Commenting
        Permission
        Disabled Forbidden Owners Signed-in users Everyone
      • Enable
      • Permission
        • Forbidden
        • Owners
        • Signed-in users
        • Everyone
      • Suggest edit
        Permission
        Disabled Forbidden Owners Signed-in users Everyone
      • Enable
      • Permission
        • Forbidden
        • Owners
        • Signed-in users
      • Emoji Reply
      • Enable
      • Versions and GitHub Sync
      • Note settings
      • Note Insights New
      • Engagement control
      • Make a copy
      • Transfer ownership
      • Delete this note
      • Save as template
      • Insert from template
      • Import from
        • Dropbox
        • Google Drive
        • Gist
        • Clipboard
      • Export to
        • Dropbox
        • Google Drive
        • Gist
      • Download
        • Markdown
        • HTML
        • Raw HTML
    Menu Note settings Note Insights Versions and GitHub Sync Sharing URL Create Help
    Create Create new note Create a note from template
    Menu
    Options
    Engagement control Make a copy Transfer ownership Delete this note
    Import from
    Dropbox Google Drive Gist Clipboard
    Export to
    Dropbox Google Drive Gist
    Download
    Markdown HTML Raw HTML
    Back
    Sharing URL Link copied
    /edit
    View mode
    • Edit mode
    • View mode
    • Book mode
    • Slide mode
    Edit mode View mode Book mode Slide mode
    Customize slides
    Note Permission
    Read
    Only me
    • Only me
    • Signed-in users
    • Everyone
    Only me Signed-in users Everyone
    Write
    Only me
    • Only me
    • Signed-in users
    • Everyone
    Only me Signed-in users Everyone
    Engagement control Commenting, Suggest edit, Emoji Reply
  • Invite by email
    Invitee

    This note has no invitees

  • Publish Note

    Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note No publishing access yet

    Your note will be visible on your profile and discoverable by anyone.
    Your note is now live.
    This note is visible on your profile and discoverable online.
    Everyone on the web can find and read all notes of this public team.

    Your account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

    Your team account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

    Explore these features while you wait
    Complete general settings
    Bookmark and like published notes
    Write a few more notes
    Complete general settings
    Write a few more notes
    See published notes
    Unpublish note
    Please check the box to agree to the Community Guidelines.
    View profile
    Engagement control
    Commenting
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    • Everyone
    Suggest edit
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    Emoji Reply
    Enable
    Import from Dropbox Google Drive Gist Clipboard
       Owned this note    Owned this note      
    Published Linked with GitHub
    • Any changes
      Be notified of any changes
    • Mention me
      Be notified of mention me
    • Unsubscribe
    # [ChipNet: Real-Time LiDAR Processing for Drivable Region Segmentation on an FPGA](https://arxiv.org/pdf/1808.03506.pdf) ## [Github](https://github.com/hashi0203/ChipNet-LiDAR-Segmentation) ## Algorithm Design ### A. LiDAR data preparation KITTI使用的是64線的光達。通常,database裡面會包含x、y、z座標,以及物體反射強度r,如圖一(a)。從點雲投影至相機視角,如圖一(b),或是原始光達視角,如圖一(c\),在空間分佈的密度都不同。因此需要針對光達所掃出來的點進行重新修改座標、採樣。 ![](https://i.imgur.com/pxGpvXf.png) > 反射強度 -> 會受物體、角度等影響 如表一所示,並沒有統一的點雲座標與視角形式。又由於,大量的LiDAR點,容易散佈在ROI。因此,非ROI區域,稀疏性是較高的。需要耗費大量運算資源來處理”0”。 > 座標 -> sampling view > 視角 -> space subdivision > ROI -> Region of interesting ![](https://i.imgur.com/q9kxKfX.png) 因此,本文使用球座標系。在角方位\[-45º, 45º)為ROI區域,並將64線分別進行切割。在每一行上,每0.5º進行切割。因此,ROI的所有點,會散佈在180*64的網格當中。會使用0.5º,是因為他為角分辨率的3倍,因此每個網格中,會存在至少兩個點。然而實際上,可能會受強度影響,造成空洞現象。根據採樣,會存留14個特徵點,分別為7個較近的掃描點,與7個較遠的掃描點。這7個又可分為笛卡爾坐標x、y、z、球坐標θ、φ、ρ和激光反射強度r。 如表一所示,球座標系具有較高的ROI點雲使用率,稀疏度也較為密集。 ### B. ChipNet: a hardware friendly and extendable CNN architecture #### 1) ChipNet convolutional block: ![](https://i.imgur.com/knQTF6m.png) ChipNet的block如圖四所示,它包括三個分支。第一個分支使用殘差方式,將Input直接連接至output,減少梯度消失及爆炸。第二個分支使用一般的3*3卷積。第三個分支為一個3*3的擴張卷積,用於處理更多資料,但是減少參數及運算量。使用此block,能夠有更穩定的梯度及更少的參數。ChipNet的block僅有73856個參數、8.02億次乘法。傳統的5x5卷積,需要102464個參數,11.8億次乘法。ChipNet的block減少28%的參數量、32%的乘法量。 #### 2) ChipNet network architecture: ![](https://i.imgur.com/fKKTjJL.png) 架構如表二所示,ConvEncoder會將張量從14提升至64。隨後經過10次的ChipNetBlock。最後輸出透過channel-wise mapping將輸出改為180*64*1。 #### 3) Simulated quantization: 使用Fixed point在FPGA領域中,優於浮點數。他能夠減少硬體資源、內存、Clock。 然而,並不能直接將float轉成fixed point,這可能會丟失一些訊息。因此,本文提出一種量化的方式,來訓練神經網路。 ##### Simulated quantization of weights and variables: 在[[21]](https://arxiv.org/pdf/1712.05877.pdf)的reference中,在反向傳播的權重與梯度會被存成float,正向傳播會將數值量化成fixed point。優點是權重和梯度在連續空間中更新,因此可以避免由於量化引起的局部最優。缺點為在tensorflow中,需要修改一些特定函數。 ![](https://i.imgur.com/CT1XSYc.png) 本文提出一個權重調節器。如Algorithm 1.所示。其實就是將數值左移F位,進行四捨五入,最後在右移F位,將數值轉為N位元的小數。在過程中,不使用tensorflow的BP,因此使用StopGradient。 ![](https://i.imgur.com/6lufw5X.png) ##### Evaluation of quantization: 本文使用ford的dataset進行chipnet的訓練、量化、微調。如表三所示,將數值精度降低,並不會造成精度下降。 ![](https://i.imgur.com/MwVTR8M.png) ### C. View of drivable region 網路輸出後的結果為車輛前20m寬40m的俯視,會進行後處理,將輸出投影至頂視圖。因為他與KITTI的格式相同,容易進行比較。 ![](https://i.imgur.com/OZCGaN5.png) 如Algorithm 2.所示。1, 2, 3主要針對模型輸出進行輪廓提取,4, 5主要針對輪廓進行填充,將區域內的點逐格標記。 後處理使用[GridMap](https://github.com/ANYbotics/grid_map)在CPU上實現。內部包含iterator,能夠將區域內的點逐格標記。 ![](https://i.imgur.com/6epPdlS.gif)![](https://i.imgur.com/O1s5tOR.gif)![](https://i.imgur.com/zoU1e04.gif)![](https://i.imgur.com/d33c8xI.gif)![](https://i.imgur.com/vgm133u.gif)![](https://i.imgur.com/kl0pVbl.gif)![](https://i.imgur.com/Fu92gqy.gif) 在CPU處理上,能狗以每幀5ms處理。 後處理會造成精度下降可分為兩部分。1. 投影至鳥瞰圖時,LiDAR在較遠處的點雲較為稀疏,轉換時可能會造成失真。2. 在Algorithm 2. 時,假設外部區域為不可駕駛,內部區域為可駕駛,因此,如果可駕駛區域包含空洞時,可能會造成誤差。最後使用KITTI進行頻估,將結果與KITTI的鳥瞰圖進行比較,F1-Score為95.5%。 ### D. Network training and evaluation ChipNet在Xeon 2.4 GHz CPU 和 NVidia K20 GPU的平台,並使用Keras進行訓練。輸入為180*64*14的tensor輸出為180*64*1的tensor。每幀為256ms。使用Ford與KITTI的資料集進行頻估。 Ford的資料集3871筆資料。LiDAR使用10Hz進行採樣。由於資料集本身沒進行Label,因此本文手動標記ROI區域。為減少連續幀數重複性,因此每5幀為一個單位。實際上,1秒內能被採用2幀。在數據集中,刪除一些off-road的的樣本。因此,在Ford的資料集中,總共包含600筆資料。 ![](https://i.imgur.com/yH32pU2.png) 原圖會從1243*1616剪裁至與LiDAR大小相同的800*600。Algorithm 4.表示LiDAR轉至camera view的演算法。本文使用400筆資料進行訓練/驗證,200筆進行測試。在400筆中,使用(-10, -5, 0, 5, 10)º進行旋轉,增加訓練樣本。因此總共有2000筆訓練資料。 本文使用Cross entropy當作loss function,adam當作optimizer。首先在沒使用量化的方式對網路進行30次迭代(4.5hr),隨後使用量化方式進行10次迭代(1.5hr),以獲得fixed point權重。 在測試階段,使用F1 score (F1)、average precision (AP)、precision (PRE)、recall (REC)、false positive rate (FPR)、false negative rate (FNR)當作評估指標。表三為不同bit情況下的評估結果。本文最終選擇18bit當作FPGA實現目標。 本文也在KITTI進行評估。包括289筆train data與290筆test data。圖片會被剪裁至375*1242,與Ford不同,KITTI是在鳥瞰圖進行評估。 在訓練時,將資料進行(–10, -8, -6, -4, -2, 0, 2, 4, 6, 8, 10)º旋轉,來擴增資料集。總共包括3179筆資料,其中3000筆進行訓練,179筆進行測試。訓練時,使用Ford前30次的迭代當作pretrain,隨後僅用KITTI的dataset進行10次的迭代(2.05hr)。 ![](https://i.imgur.com/irZokw0.png)![](https://i.imgur.com/wHC9vYk.png) 表4為KITTI的實驗結果,並與其他學者進行比較。紅色區域為假駕駛區、藍色區域為缺失駕駛區、綠色區域為正確駕駛區、其餘部分為正確非駕駛區。 ## Hardware Architecture ![](https://i.imgur.com/HgItCku.png)![](https://i.imgur.com/RLBcsli.png) ![](https://i.imgur.com/cSVcEuh.png)![](https://i.imgur.com/Hyy7Pl8.png) ![](https://i.imgur.com/vQblPIf.png)![](https://i.imgur.com/uhgy6W7.png) Clock 350MHz Xilinx UltraScale XCKU115 FPGA-> 12.59ms NVidia K20 GPU-> 162ms Intel Core i5-5200U CPU-> 549ms FPGA 實現的速度比 CPU 快 43 倍,比 GPU 快 13 倍。 以FPGA進行LiDAR運算文章較少,無法比較。 所提出的 FPGA 解決方案的功耗僅為 NVidia K20 GPU 的 11.8%,即 107 W。

    Import from clipboard

    Paste your markdown or webpage here...

    Advanced permission required

    Your current role can only read. Ask the system administrator to acquire write and comment permission.

    This team is disabled

    Sorry, this team is disabled. You can't edit this note.

    This note is locked

    Sorry, only owner can edit this note.

    Reach the limit

    Sorry, you've reached the max length this note can be.
    Please reduce the content or divide it to more notes, thank you!

    Import from Gist

    Import from Snippet

    or

    Export to Snippet

    Are you sure?

    Do you really want to delete this note?
    All users will lose their connection.

    Create a note from template

    Create a note from template

    Oops...
    This template has been removed or transferred.
    Upgrade
    All
    • All
    • Team
    No template.

    Create a template

    Upgrade

    Delete template

    Do you really want to delete this template?
    Turn this template into a regular note and keep its content, versions, and comments.

    This page need refresh

    You have an incompatible client version.
    Refresh to update.
    New version available!
    See releases notes here
    Refresh to enjoy new features.
    Your user state has changed.
    Refresh to load new user state.

    Sign in

    Forgot password
    or
    Sign in via Google Sign in via Facebook Sign in via X(Twitter) Sign in via GitHub Sign in via Dropbox Sign in with Wallet
    Wallet ( )
    Connect another wallet

    New to HackMD? Sign up

    By signing in, you agree to our terms of service.

    Help

    • English
    • 中文
    • Français
    • Deutsch
    • 日本語
    • Español
    • Català
    • Ελληνικά
    • Português
    • italiano
    • Türkçe
    • Русский
    • Nederlands
    • hrvatski jezik
    • język polski
    • Українська
    • हिन्दी
    • svenska
    • Esperanto
    • dansk

    Documents

    Help & Tutorial

    How to use Book mode

    Slide Example

    API Docs

    Edit in VSCode

    Install browser extension

    Contacts

    Feedback

    Discord

    Send us email

    Resources

    Releases

    Pricing

    Blog

    Policy

    Terms

    Privacy

    Cheatsheet

    Syntax Example Reference
    # Header Header 基本排版
    - Unordered List
    • Unordered List
    1. Ordered List
    1. Ordered List
    - [ ] Todo List
    • Todo List
    > Blockquote
    Blockquote
    **Bold font** Bold font
    *Italics font* Italics font
    ~~Strikethrough~~ Strikethrough
    19^th^ 19th
    H~2~O H2O
    ++Inserted text++ Inserted text
    ==Marked text== Marked text
    [link text](https:// "title") Link
    ![image alt](https:// "title") Image
    `Code` Code 在筆記中貼入程式碼
    ```javascript
    var i = 0;
    ```
    var i = 0;
    :smile: :smile: Emoji list
    {%youtube youtube_id %} Externals
    $L^aT_eX$ LaTeX
    :::info
    This is a alert area.
    :::

    This is a alert area.

    Versions and GitHub Sync
    Get Full History Access

    • Edit version name
    • Delete

    revision author avatar     named on  

    More Less

    Note content is identical to the latest version.
    Compare
      Choose a version
      No search result
      Version not found
    Sign in to link this note to GitHub
    Learn more
    This note is not linked with GitHub
     

    Feedback

    Submission failed, please try again

    Thanks for your support.

    On a scale of 0-10, how likely is it that you would recommend HackMD to your friends, family or business associates?

    Please give us some advice and help us improve HackMD.

     

    Thanks for your feedback

    Remove version name

    Do you want to remove this version name and description?

    Transfer ownership

    Transfer to
      Warning: is a public team. If you transfer note to this team, everyone on the web can find and read this note.

        Link with GitHub

        Please authorize HackMD on GitHub
        • Please sign in to GitHub and install the HackMD app on your GitHub repo.
        • HackMD links with GitHub through a GitHub App. You can choose which repo to install our App.
        Learn more  Sign in to GitHub

        Push the note to GitHub Push to GitHub Pull a file from GitHub

          Authorize again
         

        Choose which file to push to

        Select repo
        Refresh Authorize more repos
        Select branch
        Select file
        Select branch
        Choose version(s) to push
        • Save a new version and push
        • Choose from existing versions
        Include title and tags
        Available push count

        Pull from GitHub

         
        File from GitHub
        File from HackMD

        GitHub Link Settings

        File linked

        Linked by
        File path
        Last synced branch
        Available push count

        Danger Zone

        Unlink
        You will no longer receive notification when GitHub file changes after unlink.

        Syncing

        Push failed

        Push successfully