geolocate-from-pixels

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Geolocate from pixels

从像素进行地理定位

Every photograph taken outdoors contains enough information to place it. The constraint is never the image; it is your patience and your reference knowledge.

The beginner mistake is searching before inventorying. People see a mountain, type "mountain with two peaks" into a search box, and get nothing. The method is the opposite: extract every clue first, rank them by how much of the planet each one eliminates, and only then start searching — because the clue that pins the country is usually not the one your eye went to.

每一张户外拍摄的照片都包含足够的定位信息。限制因素从来不是图像本身，而是你的耐心和参考知识储备。

新手常犯的错误是先搜索再梳理线索。人们看到一座山，就在搜索框里输入“双峰山”，结果一无所获。正确的方法恰恰相反：先提取所有线索，按照线索能排除的全球范围大小排序，之后再开始搜索——因为能锁定国家的线索往往不是你第一眼注意到的那个。

Rank your clues before you search

搜索前先对线索排序

Work down this list. Each row eliminates far more of the world than the one below it, so a single row-one clue is worth twenty row-six clues.

Tier	Clue	What it buys you
1	Readable proper nouns — business names, street names, municipal logos, school names	Often an instant pin. A business name plus a country is a map query, not an investigation.
1	Phone numbers on signage and vehicles	Country and frequently city, from prefix and digit-grouping convention.
1	Language and script, then orthography	Script narrows to a family; specific diacritics, letter forms and spelling conventions narrow to one country and sometimes one region.
2	Licence plate format — shape, colour, band, character layout	Country, often issuing region. Visible from a long way off, survives compression.
2	Driving side	Splits the world roughly a third to two thirds. Read it from parked-car steering wheels, not just from traffic.
2	Road markings — centre-line colour, dash rhythm, edge lines	Yellow versus white centre lines alone cuts most of the world.
3	Utility pole construction and insulator style	Regionally conservative and rarely changed. One of the most reliable tells in the frame.
3	Bollards, guardrails, kerb painting, chevron markers	Nationally standardised, nationally distinctive.
3	Traffic signal mounting, lens arrangement, backboards	Overhead versus pole-side, horizontal versus vertical, extra lenses — all national conventions.
4	Signage typeface and road-sign standard	Which sign standard a country adopted, and its specific alphabet.
4	Satellite dish elevation and azimuth	Constrains latitude, and the orbital slot indicates which service region.
5	Architecture, roofing material, window and balcony conventions, rooftop tanks and heaters	Region and climate band.
5	Vegetation and biome	Latitude band, climate, hemisphere. Careful: ornamental planting is global.
6	Terrain and horizon profile	Only useful once you have a candidate region — then it is decisive.

Every variation and what it implies: reference/regional-indicators.md.

按照以下列表依次分析。每一层级的线索能排除的范围远大于下一层级，因此一个第一层级的线索抵得上二十个第六层级的线索。

层级	线索	能为你带来什么
1	可读的专有名词——企业名称、街道名称、市政标志、学校名称	通常能直接定位。企业名称加上国家信息即可直接进行地图查询，无需深入调查。
1	标识和车辆上的电话号码	根据号码前缀和数字分组规则确定国家，往往还能确定城市。
1	语言及文字体系，其次是拼写规则	文字体系可缩小到某个语系；特定变音符号、字母形态和拼写规则可缩小到单个国家，有时甚至是特定地区。
2	车牌格式——形状、颜色、条带、字符布局	确定国家，往往还能确定发证地区。从远处就能看到，且在图像压缩后仍可识别。
2	驾驶方向	将全球大致分为三分之一和三分之二的区域。可从停放车辆的方向盘位置判断，而不仅仅是交通流向。
2	道路标线——中心线颜色、虚线节奏、边缘线	仅中心线是黄色还是白色就能排除全球大部分地区。
3	电线杆结构和绝缘子样式	具有区域保守性，很少更改。是画面中最可靠的线索之一。
3	护柱、护栏、路缘涂装、V形标志	全国统一标准，具有国家辨识度。
3	交通信号灯安装方式、透镜布局、背板	悬挂式还是杆侧安装、水平还是垂直排列、额外透镜——这些都是国家通行规范。
4	标识字体和道路标志标准	国家采用的标志标准及其特定字母体系。
4	卫星天线仰角和方位角	可限制纬度范围，轨道位置则表明服务区域。
5	建筑风格、屋顶材料、窗户和阳台惯例、屋顶水箱和加热器	确定区域和气候带。
5	植被和生物群系	确定纬度带、气候、半球。注意：观赏性植物遍布全球。
6	地形和地平线轮廓	仅在已有候选区域时有用——此时它具有决定性作用。

所有变体及其含义： reference/regional-indicators.md。

Method

方法步骤

Inventory. Write a numbered list of every clue in the frame before you search anything. Include the negatives — no snow, no palms, no overhead wires — because negatives eliminate regions just as well. Zoom in on every sign, every vehicle, every pole. Run the preprocessing recipes in
```
find-the-original-image
```
to read underexposed or small detail.
Fix the country. Combine your tier-1 and tier-2 clues until they agree. If two contradict — Cyrillic signage with right-hand-drive cars — that contradiction is a finding: an imported-vehicle market, a border region, or a composited image.
Read the text properly. Transcribe, then translate, then search the transcription verbatim in the local language. Searching a translation loses you the match. If the script is unfamiliar, get the script identified before you attempt letters — Georgian, Armenian, Amharic, Khmer, Thai, Lao and Sinhala are all frequently misidentified as each other's neighbours by people guessing.
Narrow to a locality. Named businesses go into a mapping search restricted to the country. Chains are useful in reverse: a chain that only operates in three provinces eliminates the rest of the country.
Query the map for the geometry, not the place. When you have no names but you do have structure — a water tower next to a rail crossing next to a football pitch — query OpenStreetMap features directly with Overpass rather than panning around. This is the step most people skip and the one that most often works.

[out:json][timeout:90];
area["ISO3166-1"="RO"]->.a;
nwr["man_made"="water_tower"](area.a)->.t;
foreach.t -> .w (
  nwr(around.w:400)["leisure"="pitch"]["sport"="soccer"];
  out center;
);

Confirm in imagery. Match the candidate against satellite/aerial and street-level sources. Compare invariants: building footprint shape, roof colour, the count and spacing of windows, kerb line, tree positions, the exact arrangement of a fence. Do not match on things that change — parked cars, awnings, signage, foliage density.
Chronolocate. Sun position for time of day and date band, season from vegetation, weather archives for corroboration. Procedure in reference/chronolocation.md.
Score it. Three independent features aligning, or stop.

梳理线索。在搜索任何内容之前，列出画面中所有线索的编号清单。包括反向线索——无积雪、无棕榈树、无架空电线——因为反向线索同样能排除特定区域。放大查看每个标识、每辆车、每根电线杆。使用
```
find-the-original-image
```
中的预处理方法读取曝光不足或细节微小的内容。
确定国家。结合第一层级和第二层级的线索，直到它们指向一致。如果两条线索矛盾——如西里尔文字标识搭配右舵车辆——这种矛盾本身就是一个发现：可能是进口车辆市场、边境地区，或是合成图像。
准确识别文字。先转录，再翻译，然后用当地语言原文搜索转录内容。搜索译文会错失匹配结果。如果文字体系不熟悉，先确定文字体系再尝试识别字母——格鲁吉亚文、亚美尼亚文、阿姆哈拉文、高棉文、泰文、老挝文和僧伽罗文常被不熟悉的人误判为邻近地区的文字。
缩小到具体地点。将有名称的企业信息限定在对应国家内进行地图搜索。连锁品牌反向使用很有用：仅在三个省份运营的连锁品牌可排除该国其他地区。
按几何特征而非地点查询地图。当没有名称但有结构特征时——如水塔紧邻铁路道口，旁边还有足球场——直接用Overpass查询OpenStreetMap的特征，而非手动浏览。这是大多数人会跳过但往往有效的步骤。

[out:json][timeout:90];
area["ISO3166-1"="RO"]->.a;
nwr["man_made"="water_tower"](area.a)->.t;
foreach.t -> .w (
  nwr(around.w:400)["leisure"="pitch"]["sport"="soccer"];
  out center;
);

用图像验证。将候选地点与卫星/航空图像及街景图像进行比对。比对不变特征：建筑轮廓形状、屋顶颜色、窗户数量和间距、路缘线、树木位置、围栏的精确布局。不要比对可变特征——停放的车辆、遮阳篷、标识、植被密度。
时间定位。通过太阳位置确定时段和日期范围，通过植被确定季节，结合气象档案佐证。步骤详见reference/chronolocation.md。
评分确认。找到三个独立匹配特征即可停止。

Imagery sources and where each one wins

图像来源及其适用场景

Source	Reach for it when
Google Earth (desktop)	Default satellite work. The historical-imagery timeline is the reason to use the desktop client over the browser: it dates construction, demolition and earthworks.
Google Street View	Default street-level, in the countries it covers. Time-machine feature gives you dated captures of the same spot.
Yandex Maps and Panoramas	Russia, Belarus, Kazakhstan, Central Asia, the Caucasus, Turkey. Panorama coverage and satellite detail there routinely exceed Google's, and Yandex's imagery is sometimes from a different date, which is useful on its own.
Mapillary	Crowdsourced street-level. Covers roads, tracks and countries Street View cars never drove. Often the only street-level imagery for rural areas and much of Africa, South Asia and the Balkans.
KartaView	Second crowdsourced street-level set with different contributor geography. Check it when Mapillary is empty.
Bing Maps aerial and Streetside	A different capture date and sometimes a better angle. Oblique views help with building heights.
Apple Maps	Look Around coverage and high-quality 3D in major cities.
Esri World Imagery, with its Wayback archive	Versioned historical basemap imagery — a second, independent historical timeline when Google's is thin.
Copernicus/Sentinel browsers	Sentinel-2 optical at ten-metre resolution with a revisit measured in days. Too coarse for a building, ideal for dating a change: a fire scar, a flood, a new dirt road, a filled reservoir.
Landsat archive (USGS)	Thirty-metre resolution but a multi-decade record. For "when did this quarry appear".
NASA FIRMS	Thermal anomaly detections with timestamps. Dates fires, flares and large explosions to within hours.
Declassified historical imagery via USGS EarthExplorer	Pre-satellite-era-commercial coverage for very old questions.
National and municipal orthophoto portals	Frequently far higher resolution than any global provider, and dated. Search for the country's cadastral or survey agency viewer.
OpenStreetMap plus Overpass	Query by feature type rather than browsing. Also the only source for many footpaths, power lines and small structures.
Panorama generators from elevation models	Synthesises the horizon as seen from a given coordinate and bearing, for ridgeline matching.

来源	适用场景
Google Earth（桌面端）	卫星图像处理的默认选择。桌面客户端优于浏览器端的原因是其历史图像时间轴，可追踪建筑、拆除和土方工程的时间。
Google Street View	覆盖国家的默认街景工具。时光机功能可提供同一地点的历史拍摄画面。
Yandex Maps and Panoramas	俄罗斯、白俄罗斯、哈萨克斯坦、中亚、高加索地区、土耳其。其全景覆盖和卫星细节通常超过Google，且Yandex的图像拍摄日期有时不同，这本身就很有用。
Mapillary	众包街景图像。覆盖Street View车辆从未涉足的道路、小径和国家。通常是农村地区及非洲、南亚、巴尔干半岛大部分地区唯一的街景图像来源。
KartaView	第二个众包街景数据集，贡献者地理分布不同。当Mapillary无相关图像时可查看。
Bing Maps aerial and Streetside	拍摄日期不同，有时角度更佳。倾斜视图有助于判断建筑高度。
Apple Maps	Look Around覆盖范围及主要城市的高质量3D图像。
Esri World Imagery及其Wayback档案	带版本记录的历史底图图像——当Google历史图像不足时，可作为独立的第二历史时间轴。
Copernicus/Sentinel浏览器	Sentinel-2光学图像分辨率为10米，重访周期以天计算。分辨率不足以定位单个建筑，但非常适合追踪变化：火灾痕迹、洪水、新修土路、水库蓄水情况。
Landsat档案（USGS）	分辨率30米，但有几十年的记录。适用于“这个采石场何时出现”这类问题。
NASA FIRMS	带时间戳的热异常检测。可将火灾、 flare和大型爆炸的发生时间定位到数小时内。
USGS EarthExplorer提供的解密历史图像	适用于非常早期的问题，覆盖商业卫星时代之前的内容。
国家和市政正射影像门户	分辨率通常远高于任何全球提供商，且带有拍摄日期。搜索对应国家的地籍或测绘机构查看器即可。
OpenStreetMap加Overpass	按特征类型查询而非浏览。也是许多步道、电线和小型建筑的唯一信息来源。
基于高程模型的全景生成器	合成从给定坐标和方位看到的地平线，用于山脊线匹配。

Where this goes wrong

常见误区

Confirmation bias is the failure mode of this discipline. You will find a building that looks right and then start explaining away the differences. Set your falsification criteria before you look: "if the pole on the left is on the wrong side of the road, this candidate is dead." Then honour them.
Imagery is dated, and you are comparing across time. A missing building may have been demolished; a present one may be newer than the photo. Check the capture date of the imagery, and check the historical timeline before you reject a candidate.
Ornamental and introduced vegetation lies constantly. Eucalyptus grows on five continents. Palms are planted far outside their native range. Vegetation is a tier-five clue for a reason — it corroborates, it does not decide.
Global brands and franchised signage tell you almost nothing except where a company operates. A ubiquitous fast-food logo is not a clue; the local-language sub-brand and phone number on the same sign are.
Compression invents detail. Text you "read" at the JPEG artifact level is frequently not there. If a plate or a sign only becomes legible after upscaling, it is a hypothesis, not a reading. Go back to the original pixels.
Reflections and mirrors flip everything. Text in a shop window, or a scene shot into a mirror, reverses. So does a mirrored repost. If the driving side and the text direction disagree, suspect a flip before you suspect a country.
Photos are not necessarily of one place. Composites exist, and a video can be cut from footage of several locations. Geolocating one frame does not geolocate the video. Verify frames independently, and hand suspicion to
```
is-this-photo-real
```
.
Border regions and enclaves break single-clue logic. Signage, plates, currency and infrastructure all mix within a few kilometres of a border, and in territories with disputed or transitional administration.
The claim shapes what you see. If you are told the photo is from a particular city, you will find that city. Try to do the inventory before you read the caption, and when you can't, run the exercise as though the caption said somewhere else.
Long lenses compress and wide lenses stretch. Apparent distance between a foreground subject and a background mountain is a function of focal length. Do not judge "how close the hills are" without accounting for it.

确认偏差是该领域的主要失败原因。你会找到看起来匹配的建筑，然后开始解释差异。在开始搜索前就设定 falsification criteria：“如果左侧的电线杆在道路错误的一侧，这个候选地点就排除。”然后严格执行。
图像有拍摄日期，你可能在跨时间比对。照片中存在的建筑可能在参考图像拍摄时还未建成；参考图像中的建筑可能在照片拍摄后已被拆除。在排除候选地点前，先检查图像的拍摄日期和历史时间轴。
观赏性和引进植被经常误导判断。桉树生长在五大洲。棕榈树被种植在原生范围之外的许多地区。植被之所以是第五层级线索，是因为它仅用于佐证，而非决定性依据。
全球品牌和特许标识几乎无法提供有效信息，只能说明公司的运营范围。随处可见的快餐品牌标识不是线索；同一标识上的本地语言子品牌和电话号码才是。
图像压缩会生成虚假细节。在JPEG artifact级别“读取”的文字往往并不存在。如果车牌或标识只有放大后才清晰，那只是假设，而非确定的识别结果。回到原始像素重新查看。
反射和镜像会翻转所有内容。商店橱窗中的文字，或通过镜子拍摄的场景，都是反向的。镜像转发的内容也是如此。如果驾驶方向和文字方向不一致，先怀疑是镜像翻转，而非国家不符。
照片不一定拍摄于同一地点。合成图像确实存在，视频也可能由多个地点的片段剪辑而成。对一帧画面进行地理定位并不代表整个视频的定位。需独立验证每一帧，若有疑问可使用
```
is-this-photo-real
```
工具。
边境地区和飞地会打破单一线索逻辑。标识、车牌、货币和基础设施在边境几公里范围内都会混杂，在存在争议或过渡管理的地区更是如此。
先入为主的说法会影响你的判断。如果有人告诉你照片拍摄于某城市，你就会倾向于找到该城市。尽量在查看说明前梳理线索，如果做不到，就假设说明中的地点是其他地方再进行分析。
长焦镜头会压缩空间，广角镜头会拉伸空间。前景主体与背景山脉的表观距离取决于焦距。在判断“山有多近”时，必须考虑焦距因素。

Confidence grading

置信度分级

Confirmed location — a specific coordinate where at least three mutually independent, non-transient features match reference imagery: for example building footprint geometry, the position and count of utility poles, and terrain profile. Independence is the requirement — three photos of the same sign is one feature, not three. You should be able to reproduce the camera position and bearing and state a radius in metres.
Probable location — the correct locality with a plausible specific site; two independent features match, or three match but one reference source is undated or low-resolution. Express as a named place plus a radius, not a coordinate.
Region only — country or province established from tier-one and tier-two clues with no site match. This is a perfectly respectable result and is often all a case needs. Say "somewhere in this province", not a point.
Unconfirmed — a candidate that looks right but rests on transient features, a single matching element, or your own sense of resemblance.
Excluded — you can affirmatively rule the claimed location out. Often easier and more valuable than finding the true one; a disproof needs only one hard contradiction, such as driving side.

Always report a radius with a coordinate. A bare six-decimal coordinate implies sub-metre certainty you do not have.

已确认地点——特定坐标，至少三个相互独立的非瞬态特征与参考图像匹配：例如建筑轮廓几何形状、电线杆的位置和数量、地形轮廓。独立性是关键——同一标识的三张照片只是一个特征，而非三个。你应能重现相机位置和方位，并给出以米为单位的误差半径。
可能地点——正确的区域，有合理的具体地点；两个独立特征匹配，或三个特征匹配但其中一个参考来源无日期或分辨率低。表述为命名地点加误差半径，而非具体坐标。
仅确定区域——通过第一层级和第二层级线索确定国家或省份，但未匹配到具体地点。这是完全合理的结果，往往也是案件所需的全部信息。表述为“该省内某处”，而非具体点。
未确认——看起来匹配但仅基于瞬态特征、单个匹配元素或主观相似性的候选地点。
已排除——可明确否定声称的地点。这通常比找到真实地点更容易且更有价值； disproving只需一个确凿的矛盾点，比如驾驶方向不符。

给出坐标时务必附带误差半径。单纯的六位小数坐标意味着你声称有亚米级的确定性，而实际上你并不具备。

Worked example

实例演示

An image is circulated as an attack on a fuel depot "in country A". No metadata.

Inventory: white centre line, right-hand traffic, concrete utility poles with a single horizontal crossarm and stubby brown insulators, a warning sign in a Latin script with a diacritic that does not exist in country A's language, one shop sign partly legible, low scrubby vegetation, bare deciduous trees, snow patches in shadowed ground only, a mountain ridge on the left horizon.

The diacritic already contradicts the claim — that is the finding that matters. Script and orthography narrow to two neighbouring countries. The pole and insulator style matches one of them.

The shop sign OCRs to a fragment. Searching the fragment as a business name gives a chain with outlets in one province. Overpass query for fuel depots within that province returns eleven candidates.

First candidate looks right in satellite view — same tank count. Killed by the falsification test: the access road approaches from the wrong side and the ridge would be behind the camera. Dead end, and a good one, because it was cheap.

Fourth candidate matches on tank arrangement, the perimeter fence corner, and the ridgeline profile generated from elevation data for that viewpoint. Street-level crowdsourced imagery from a nearby road shows the same pole line.

Chronolocation: shadow azimuth and a shadow-length ratio off the fence post give mid-morning and a solar elevation consistent with two date bands. Snow in shade only, plus bare deciduous trees, selects the late-winter band over the early-autumn one. A weather archive for the nearest station shows precipitation days earlier and clear skies that morning, consistent.

Result: location confirmed, 100 m radius, in country B not country A. Date probable to a two-week window. Time of day probable, mid-morning local.

一张被传播为“在A国袭击燃料库”的图像，无元数据。

线索梳理：白色中心线、右舵交通、带单根水平横臂和短粗棕色绝缘子的混凝土电线杆、带有A国语言中不存在的变音符号的拉丁语警示标识、部分可辨认的商店招牌、低矮灌木丛、落叶树光秃、仅阴影区域有积雪、左侧地平线有山脊。

变音符号已与声称的地点矛盾——这就是关键发现。文字体系和拼写规则缩小到两个邻国。电线杆和绝缘子样式匹配其中一个国家。

商店招牌OCR识别出片段。将该片段作为企业名称搜索，得到一家仅在某一省份有门店的连锁品牌。用Overpass查询该省内的燃料库，返回11个候选地点。

第一个候选地点在卫星视图中看起来匹配——油罐数量相同。但被falsification test否定：入口道路从错误方向接入，山脊会在相机后方。此路不通，但这个排除过程成本很低。

第四个候选地点在油罐布局、围栏拐角和从该视角生成的高程数据山脊线轮廓上均匹配。附近道路的众包街景图像显示了相同的电线杆排列。

时间定位：阴影方位和栅栏柱的阴影长度比表明是上午中段，太阳高度角符合两个日期范围。仅阴影区域有积雪加上落叶树光秃，选择晚冬而非初秋的日期范围。最近气象站的档案显示前几日有降水，当天上午晴朗，与此相符。

结果：地点已确认，误差半径100米，位于B国而非A国。日期可能在两周窗口内。时段可能为当地上午中段。

Pivots

关联工具

What you got	Send to
Coordinates and radius	`where-was-this-taken` , `write-the-intel-brief`
Business name, chain, municipal body	`x-ray-a-company` , `who-really-owns-it`
Phone number from signage	`whose-number-is-this`
Company website on a sign or vehicle	`who-owns-this-domain` , `recon-a-domain-passively`
Named individuals visible or credited	`find-anyone`
Suspected composite or generated scene	`is-this-photo-real`
Need for earlier copies to date the scene	`find-the-original-image` , `read-deleted-pages`
Aircraft or vessel identifiable in frame	`track-planes-and-ships`
Multiple locations to relate to one another	`graph-the-network`

你获得的信息	可使用的工具
坐标和误差半径	`where-was-this-taken` , `write-the-intel-brief`
企业名称、连锁品牌、市政机构	`x-ray-a-company` , `who-really-owns-it`
标识上的电话号码	`whose-number-is-this`
标识或车辆上的公司网站	`who-owns-this-domain` , `recon-a-domain-passively`
可见或署名的特定个人	`find-anyone`
疑似合成或生成的场景	`is-this-photo-real`
需要更早版本来确定场景日期	`find-the-original-image` , `read-deleted-pages`
画面中可识别的飞机或船只	`track-planes-and-ships`
需要关联的多个地点	`graph-the-network`

Legal and ethical notes

法律和伦理说明

Reading public imagery and public map data is passive and lawful. Two limits are real. First, geolocating a private individual's home, school or routine from their own posted photographs is the core mechanic of stalking, and the fact that the technique is impressive does not make the output legitimate; do it for missing-persons work, authorized investigation, threat assessment, or to show someone their own exposure, and not otherwise. Publish a rounded location or a region rather than a doorstep coordinate. Second, in conflict work, publishing a precise location can endanger the people in the frame or make them a target. Both of these are judgement calls you must make explicitly and record. See ../../ETHICS.md.

查看公开图像和公开地图数据属于被动行为，是合法的。但有两个实际限制。首先，通过个人发布的照片对其住所、学校或日常活动进行地理定位是跟踪行为的核心手段，技术的巧妙性并不能使结果合法化；仅可用于失踪人员搜救、授权调查、威胁评估，或向个人展示其信息暴露风险，不得用于其他用途。发布时应使用模糊后的地点或区域，而非精确到门口的坐标。其次，在冲突相关工作中，发布精确地点可能危及画面中的人员或使其成为目标。这两种情况都需要你做出明确判断并记录。详见../../ETHICS.md。