論文地址
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.233.1475&rep=rep1&type=pdf
道路和車道檢測(cè)的最新進(jìn)展調(diào)查（Recent Progress in Road and Lane Detection - A survey）
這篇文章寫(xiě)于2014年，是關(guān)于道路和車道線感知的一個(gè)綜述。
Definition 定義
Road and lane understanding includes detecting the extent of the road, the number and position of lanes, merging, splitting and ending lanes and roads, in urban, rural and highway scenarios.
道路和車道的理解包括在城市，鄉(xiāng)村和高速公路場(chǎng)景中檢測(cè)道路的范圍，車道的數(shù)量和位置，合并、分割和終止車道和道路。
Importance 重要性
The problem of road or lane perception is a crucial enabler for Advanced Driver Assistance Systems
(ADAS).
道路或車道感知問(wèn)題是高級(jí)駕駛員輔助系統(tǒng)（ADAS）的關(guān)鍵推動(dòng)因素。
Reasons 問(wèn)題
The main reasons for that are significant gaps in research, high reliability demands and large diversity in case conditions.
其主要原因是研究方面的重大差距，高可靠性要求以及案例條件的多樣性。
Relevant modalities 相關(guān)方式
- Vision: Vision modality, or more simply put, a camera, is the most frequently used modality for lane and road perception.
視覺(jué)：視覺(jué)方式，或更簡(jiǎn)單地說(shuō)，攝像機(jī)，是車道和道路感知最常用的方式。 - LIDAR: Light Detection And Ranging (LIDAR) represents another major possible modality for lane and road detection.
光探測(cè)和測(cè)距（LIDAR）代表了車道和道路探測(cè)的另一種主要可能方式。
Modules and techniques 模塊和技術(shù)
- Image cleaning: Here, our objective is to remove clutter, misleading imaging artifacts and irrelevant image parts. In general, methods that fall under this module’s scope can be categorized into two families: handling illumination related effects for enhanced image quality, and pruning parts of the image that are suspected as irrelevant for the confronted estimation task.
圖像清潔：處理照明相關(guān)效果以提高圖像質(zhì)量，剔除圖像中與道路及車道無(wú)關(guān)的部分。 - Feature extraction:Low level features are extracted from the image to support lane and road detection. For road detection, these typically include color and texture statistics allowing road segmentation, road patch classification or curb detection. For lane detection, evidence for lane marks is collected.
特征提?。簭膱D像中提取車道和道路檢測(cè)所需的特征。 對(duì)于道路檢測(cè)，包括顏色和紋理統(tǒng)計(jì)。 對(duì)于車道檢測(cè)，主要是車道標(biāo)記。 - Road/lane model fitting: A road and lane hypothesis is formed by fitting a road/lane model to the evidence gathered.
道路/車道模型擬合：通過(guò)所提取到的特征，對(duì)道路/車道模型進(jìn)行擬合。
Conclusions and Relevance 結(jié)論與意義
Challenges 面臨的挑戰(zhàn)
The challenges for research in the near decade are mainly of two types: extend the scope of road understanding, and increase its reliability. The first challenge is to extend current road and lane detection abilities into new domains. This challenge requires the development of new road scene representations, which are rich enough to describe multiple lanes with non linear topology, and yet can be reliably extracted and tracked from a video stream. The reliability challenge is harder than the first, at least for systems based primarily on vision. The reliability of current systems, which is enough for warning systems, may not be enough for closed-loop features, requiring error rates which are often orders of magnitude lower.
近十年的研究挑戰(zhàn)主要有兩種：擴(kuò)大道路理解范圍，提高其可靠性。第一個(gè)挑戰(zhàn)是將當(dāng)前的道路和車道檢測(cè)能力擴(kuò)展到新的領(lǐng)域。 這一挑戰(zhàn)需要開(kāi)發(fā)新的道路場(chǎng)景表示，其足夠豐富以描述具有非線性拓?fù)涞亩鄠€(gè)車道，并且可以從視頻流中可靠地提取和跟蹤?？煽啃蕴魬?zhàn)比第一次更難，至少對(duì)于主要基于視覺(jué)的系統(tǒng)而言。 對(duì)于警報(bào)系統(tǒng)而言，當(dāng)前系統(tǒng)的可靠性對(duì)于閉環(huán)特征來(lái)說(shuō)可能是不夠的，需要通常低幾個(gè)數(shù)量級(jí)的錯(cuò)誤率。
Fruitful direction 建議方向
- Use modalities other then vision when possible；在可能的情況下使用除視覺(jué)之外的其他方式
- Adopt machine learning techniques；采用機(jī)器學(xué)習(xí)技術(shù)
- A Public benchmark；A big challenge of current research is the inability to compare performance of
different methods due to the lack of public annotated benchmarks.公共基準(zhǔn)，當(dāng)前研究的一大挑戰(zhàn)是由于缺乏公開(kāi)的基準(zhǔn)測(cè)試
