谷歌推出照片拍攝地定位系統PlaNet
Google has unveiled a system that attempts to pinpoint the location of where a photograph was taken by analysing the image, as the internet group continues to experiment with advanced “machine learning” technologies.
谷歌(Google)推出了一套試圖利用圖像分析來準確定位照片拍攝地的系統，繼續圍繞先進的“機器學習”技術展開實驗。
Though at its early stages, the Californian company’s system is another example of how Silicon Valley groups are making giant strides in artificial intelligence, using the ability to crunch huge amounts of data and spot patterns to develop capabilities far beyond human brains.
儘管這套系統仍處於初級階段，但它再次突顯出硅谷(Silicon Valley)企業是如何在人工智能(AI)領域取得巨大進展的。人工智能是利用處理海量數據和從中辨識出模式的計算能力，來開發出遠勝人類大腦的智能。
Google’s latest experiment attempts solve a task that most humans find difficult: looking at a picture at random and trying to work out where it was taken.
谷歌的最新實驗旨在完成一項多數人都認爲困難的任務：瀏覽一張隨機給出的照片，然後辨別出這張照片是在哪裏拍攝的。
Humans are able to make rough guesses on where a shot has been taken based on clues in the picture, such as the type of trees in background and the architectural style of buildings. This task has proven beyond most computer systems.
人類能夠根據照片上的線索——比如背景中樹木的種類和建築物的建築風格——來對拍攝地作大致的推測。這一任務已被證實超出了大多數計算機系統的處理能力。
This week, Tobias Weyand, a computer vision specialist at Google, unveiled a system called PlaNet, that is able to decipher where a photograph has been taken by analysing the pixels it contains.
本週，谷歌計算機視覺處理專家託拜厄斯•韋安德(Tobias Weyand)發佈了這個名爲PlaNet的系統。該系統可以通過分析照片中包含的像素來判斷出拍攝地。
“We think PlaNet has an advantage over humans because it has seen many more places than any human can ever visit and has learnt subtle cues of different scenes that are even hard for a well-travelled human to distinguish,” Mr Weyand told MIT Technology Review, which first reported the news.
“我們認爲PlaNet相對於人類擁有一個優勢，它所見過的地方比任何一個人可能前往的地方都多得多，並且它掌握不同場景的細微線索，而即使是那些經常旅行的人也很難辨識出這些線索，”韋安德向《麻省理工科技評論》(MIT Technology Review)表示。這份雜誌最先報道了這則消息。
His team divided the world into a grid containing 26,000 squares — each one representing a specific geographical area.
韋安德的團隊將世界劃分爲一個網格，其中包含2.6萬個方格，每個方格代表一個具體的地理區域。
For every square, the scientists created a database of images derived from the internet that could be identified by their “geolocation” — the digital signatures that show where many photographs are taken. This database was made up of 126m images.
科學家們爲這些方格建立了一個圖片數據庫，所有圖片均來自互聯網、並以各自的“地理定位”（即顯示照片拍攝地的數字簽名）爲標識符。該數據庫包含1.26億張圖片。
Using this information, the team would teach a neural network — a computer system modelled on how layers of neurons in the brain interact — to place each image to a specific place.
該團隊將利用這些信息訓練一個神經網絡——模擬大腦皮層神經元交互的計算機系統——學會如何把每張圖片對應一個具體的地點。
Mr Weyand’s team plugged 2.3m geotagged images from Flickr, the online photo library, to see whether the system could correctly determine their location.
韋安德的團隊用230萬張來自在線圖片庫Flickr的包含地理位置標籤的圖片，來檢驗該系統能否正確判斷出圖片的拍攝地。
Though this means it is far from perfect, this performance is far better than humans. According to the team’s findings, the “median human localisation error” — meaning the median distance from where a person guessed the location of a picture, to where it was actually taken — is 2,320.75km. PlaNet’s median localisation error is 1,131.7km.
儘管結果表明該系統遠未達到完美，但其表現遠勝人類。該團隊的研究發現顯示，“人類定位誤差中值”——即一個人所猜的拍攝地距真正拍攝地的距離的中值——是2320.75公里。PlaNet的定位誤差中值是1131.7公里。
