Behavior recognition is already starting to move towards some scenarios, although it needs to be more sophisticated technically.
According to the "2019-2024 Research Report on China's Machine Vision Industry Prospects and Investment Opportunities" released by the China Business Industry Research Institute, the scale of China's machine vision market exceeded 10 billion yuan for the first time in 2018; , the machine vision market will further expand,It is estimated that the machine vision market will reach nearly 12.5 billion yuan in 2019.
It is true that the market size of the CV (machine vision) industry is not small and profitable, but when technology products mature and start to be applied, how to eat this cake has become the biggest problem faced by many CV startups. . At the same time, continuous losses and profit pressure are also urging every CV company to “run”.
趨視(shì)科(kē)技并不屬于CV領域最知名的(de)行(xíng)業，然而它們(men)卻在落地(dì)應用和(hé)盈利上先人一(yī)步，其公司創始人徐飙表示："If 90% of companies in the industry are losing money, we belong to the other 10%."
how do they do it
Figure | Xu Biao, founder of Truthvision Technology
CV not only has face recognition, but also behavior analysis
When it comes to CV, attention and topics are often concentrated in the field of face recognition. SenseTime, Megvii, etc. are the focus of attention both inside and outside the industry, but CV is not equivalent to face recognition, it also includes behavior recognition. Xu Biao introduced that since its establishment, Truthvision Technology has always aimed at behavior recognition.
“行(xíng)為(wèi)識别就是識别人類或者車的(de)行(xíng)為(wèi)，Such as people's fighting behavior, car running red light behavior and so on. Although both belong to machine vision, face recognition and behavior recognition are two technologies and different fields. "
At the technical level, face recognition can be completed through a photo, while behavior recognition needs to be judged by combining continuous data, because behavior itself is a continuous and dynamic process.in short,Face recognition solves the problem of who the target is, and behavior solves what kind of thing.At present, behavior recognition is often used in judicial management, smart stores,intelligent
Xu Biao told us: "There are many fields where behavior recognition is applicable, but because the technology is not mature enough, it is difficult for behavior recognition technology to play a very good role in the face of too complex and non-standard scenes. Therefore, this technology can only It is first applied in some vertical scenarios, and gradually accumulated and improved in the process of application, so as to expand to more scenarios, and finally meet the requirements of human behavior cognition in a large range."
So what are the technical difficulties of behavior recognition?
Since behavior is diverse, it includes individual behavior and group behavior, and each behavior is expressed in different ways. For example, fighting and stealing, fighting between individuals and fighting between groups are completely different.Therefore, behavior recognition faces great difficulties at the data collection level, which mainly involve problems such as occlusion and dislocation.
At the same time, the angle of human viewing the world is three-dimensional, and the picture captured by the camera is two-dimensional, so there will be a person in the video showing an arm, but because the distance parameter cannot be collected in the video,所以遮擋、錯位的(de)現象會讓AI算法難以判斷。
其次學(xué)習數據欠缺。衆所周知，許多AI技術依靠深度學(xué)習算法模型去(qù)訓練，這導緻要讓AI實現行(xíng)為(wèi)識别，就必須先給行(xíng)為(wèi)下定義，讓AI知道(dào)行(xíng)為(wèi)是什麼。然而前面已經提到行(xíng)為(wèi)非常複雜，甚至很多時候AI需要學(xué)習判斷的(de)是負面行(xíng)為(wèi)，因此企業很難獲取到大量的(de)學(xué)習數據。而算法模型沒有(yǒu)經過大量數據去(qù)訓練，也就很難“聰明”起來，從而在識别的(de)效果和(hé)精度上難以達到用戶需求。
不過盡管在技術上需要更加精進，但行(xíng)為(wèi)識别已經開始走向一(yī)些場景。
CV企業破冰關鍵：規模化
徐飙介紹：“公司一(yī)開始關注的(de)就是行(xíng)業落地(dì)而非通用場景，且瞄準的(de)第一(yī)個領域就是司法領域行(xíng)業的(de)管理(lǐ)，比如(rú)監獄管理(lǐ)，是否有(yǒu)犯人打鬥、翻牆、攀爬等。這對于司法領域的(de)管理(lǐ)而言是一(yī)個剛需，能夠降低(dī)人力管理(lǐ)成本，提升管理(lǐ)質量。”
而行(xíng)業落地(dì)和(hé)通用場景落地(dì)兩條路徑的(de)最大區别，在徐飙看來，前者能夠助力企業快速實現規模化落地(dì)，而這至關重要。
他談到：“所有(yǒu)CV廠商(shāng)在近年(nián)來特别強調落地(dì)，本質上就是規模化落地(dì)，即企業在一(yī)個項目試點實現技術落地(dì)後能夠快速複制到下一(yī)個同類型的(de)場景中，而不是做(zuò)完一(yī)個試點，下一(yī)個場景再重新做(zuò)一(yī)遍，這無疑增加了許多成本。”
對于企業而言，要實現規模化落地(dì)首先在最初尋找落地(dì)行(xíng)業時，就要找到能夠實現規模化、可(kě)複制性強的(de)場景。其中的(de)關鍵在于，企業對于用戶核心訴求的(de)把握是否精确。徐飙認為(wèi)，CV企業要實現規模化必須了解用戶的(de)需求，所謂需求指的(de)不僅是用戶對于功能的(de)需求，還包括用戶對性能當中準确度的(de)要求。
“這需要碰撞。有(yǒu)些時候沒有(yǒu)人會告訴你他的(de)需求和(hé)對準确度的(de)要求是什麼，企業往往需要通過試點、交流、反饋、修正......逐步形成一(yī)個行(xíng)業共識，而并非單個客戶的(de)需求。”
但即便把握了用戶需求和(hé)性能指标并不足夠，企業還要評估自(zì)身的(de)技術體系、優勢能否滿足用戶的(de)需求和(hé)指标。最後企業還要考慮實現規模化之後，是否會被競品取代，這要求其必須在技術落地(dì)應用過程中打造自(zì)身的(de)技術門檻，如(rú)此廠商(shāng)們(men)才能率先占領市(shì)場，并在後續的(de)競争中獲勝。
回到趨視(shì)科(kē)技自(zì)身，徐飙談道(dào)：“公司明年(nián)的(de)短(duǎn)期計劃，一(yī)方面是确保在司法行(xíng)業實現規模化，創造更多的(de)收益；同時也會将技術落地(dì)到智慧門店場景。小規模化帶給我(wǒ)們(men)盈利，也驗證了技術已經達到可(kě)複制狀态，所以我(wǒ)們(men)将會向更大的(de)市(shì)場進行(xíng)布局。”
【鎂客·請講】欄目 策劃&撰寫：溫暖