人体关键点检测产线中包含了行人检测模块和关键点检测模块，有若干模型可供选择，您可以根据下边的 benchmark 数据来选择使用的模型。如您更考虑模型精度，请选择精度较高的模型，如您更考虑模型推理速度，请选择推理速度较快的模型，如您更考虑模型存储大小，请选择存储大小较小的模型。
| 模型 | mAP(0.5:0.95) | mAP(0.5) | GPU推理耗时（ms） | CPU推理耗时 (ms) | 模型存储大小（M） | 介绍 |
|---|---|---|---|---|---|---|
| PP-YOLOE-L_human | 48.0 | 81.9 | 32.8 | 777.7 | 196.02 | 基于PP-YOLOE的行人检测模型 |
| PP-YOLOE-S_human | 42.5 | 77.9 | 15.0 | 179.3 | 28.79 |
| 模型 | 方案 | 输入尺寸 | AP(0.5:0.95) | GPU推理耗时（ms） | CPU推理耗时 (ms) | 模型存储大小（M） | 介绍 |
|---|---|---|---|---|---|---|---|
| PP-TinyPose_128x96 | Top-Down | 128*96 | 58.4 | 4.9 | PP-TinyPose 是百度飞桨视觉团队自研的针对移动端设备优化的实时关键点检测模型，可流畅地在移动端设备上执行多人姿态估计任务 | ||
| PP-TinyPose_256x192 | Top-Down | 256*192 | 68.3 | 4.9 |
paddlex --get_pipeline_config human_keypoint_detection
执行后，人体关键点检测产线配置文件将被保存在当前路径。若您希望自定义保存位置，可执行如下命令（假设自定义保存位置为./my_path）：
paddlex --get_pipeline_config human_keypoint_detection --save_path ./my_path
对于服务提供的所有操作：
200，响应体的属性如下：| 名称 | 类型 | 含义 |
|---|---|---|
errorCode |
integer |
错误码。固定为0。 |
errorMsg |
string |
错误说明。固定为"Success"。 |
响应体还可能有result属性，类型为object，其中存储操作结果信息。
| 名称 | 类型 | 含义 |
|---|---|---|
errorCode |
integer |
错误码。与响应状态码相同。 |
errorMsg |
string |
错误说明。 |
服务提供的操作如下：
infer获取图像OCR结果。
POST /ocr
| 名称 | 类型 | 含义 | 是否必填 |
|---|---|---|---|
image |
string |
服务可访问的图像文件的URL或图像文件内容的Base64编码结果。 | 是 |
inferenceParams |
object |
推理参数。 | 否 |
inferenceParams的属性如下：
| 名称 | 类型 | 含义 | 是否必填 |
|---|---|---|---|
maxLongSide |
integer |
推理时，若文本检测模型的输入图像较长边的长度大于maxLongSide，则将对图像进行缩放，使其较长边的长度等于maxLongSide。 |
否 |
result具有如下属性：| 名称 | 类型 | 含义 |
|---|---|---|
texts |
array |
文本位置、内容和得分。 |
image |
string |
OCR结果图，其中标注检测到的文本位置。图像为JPEG格式，使用Base64编码。 |
texts中的每个元素为一个object，具有如下属性：
| 名称 | 类型 | 含义 |
|---|---|---|
poly |
array |
文本位置。数组中元素依次为包围文本的多边形的顶点坐标。 |
text |
string |
文本内容。 |
score |
number |
文本识别得分。 |
result示例如下：
{
"texts": [
{
"poly": [
[
444,
244
],
[
705,
244
],
[
705,
311
],
[
444,
311
]
],
"text": "北京南站",
"score": 0.9
},
{
"poly": [
[
992,
248
],
[
1263,
251
],
[
1263,
318
],
[
992,
315
]
],
"text": "天津站",
"score": 0.5
}
],
"image": "xxxxxx"
}
import base64
import requests
API_URL = "http://localhost:8080/ocr" # 服务URL
image_path = "./demo.jpg"
output_image_path = "./out.jpg"
# 对本地图像进行Base64编码
with open(image_path, "rb") as file:
image_bytes = file.read()
image_data = base64.b64encode(image_bytes).decode("ascii")
payload = {"image": image_data} # Base64编码的文件内容或者图像URL
# 调用API
response = requests.post(API_URL, json=payload)
# 处理接口返回数据
assert response.status_code == 200
result = response.json()["result"]
with open(output_image_path, "wb") as file:
file.write(base64.b64decode(result["image"]))
print(f"Output image saved at {output_image_path}")
print("\nDetected texts:")
print(result["texts"])
#include <iostream>
#include "cpp-httplib/httplib.h" // https://github.com/Huiyicc/cpp-httplib
#include "nlohmann/json.hpp" // https://github.com/nlohmann/json
#include "base64.hpp" // https://github.com/tobiaslocker/base64
int main() {
httplib::Client client("localhost:8080");
const std::string imagePath = "./demo.jpg";
const std::string outputImagePath = "./out.jpg";
httplib::Headers headers = {
{"Content-Type", "application/json"}
};
// 对本地图像进行Base64编码
std::ifstream file(imagePath, std::ios::binary | std::ios::ate);
std::streamsize size = file.tellg();
file.seekg(0, std::ios::beg);
std::vector<char> buffer(size);
if (!file.read(buffer.data(), size)) {
std::cerr << "Error reading file." << std::endl;
return 1;
}
std::string bufferStr(reinterpret_cast<const char*>(buffer.data()), buffer.size());
std::string encodedImage = base64::to_base64(bufferStr);
nlohmann::json jsonObj;
jsonObj["image"] = encodedImage;
std::string body = jsonObj.dump();
// 调用API
auto response = client.Post("/ocr", headers, body, "application/json");
// 处理接口返回数据
if (response && response->status == 200) {
nlohmann::json jsonResponse = nlohmann::json::parse(response->body);
auto result = jsonResponse["result"];
encodedImage = result["image"];
std::string decodedString = base64::from_base64(encodedImage);
std::vector<unsigned char> decodedImage(decodedString.begin(), decodedString.end());
std::ofstream outputImage(outPutImagePath, std::ios::binary | std::ios::out);
if (outputImage.is_open()) {
outputImage.write(reinterpret_cast<char*>(decodedImage.data()), decodedImage.size());
outputImage.close();
std::cout << "Output image saved at " << outPutImagePath << std::endl;
} else {
std::cerr << "Unable to open file for writing: " << outPutImagePath << std::endl;
}
auto texts = result["texts"];
std::cout << "\nDetected texts:" << std::endl;
for (const auto& text : texts) {
std::cout << text << std::endl;
}
} else {
std::cout << "Failed to send HTTP request." << std::endl;
return 1;
}
return 0;
}
import okhttp3.*;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.fasterxml.jackson.databind.JsonNode;
import com.fasterxml.jackson.databind.node.ObjectNode;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.util.Base64;
public class Main {
public static void main(String[] args) throws IOException {
String API_URL = "http://localhost:8080/ocr"; // 服务URL
String imagePath = "./demo.jpg"; // 本地图像
String outputImagePath = "./out.jpg"; // 输出图像
// 对本地图像进行Base64编码
File file = new File(imagePath);
byte[] fileContent = java.nio.file.Files.readAllBytes(file.toPath());
String imageData = Base64.getEncoder().encodeToString(fileContent);
ObjectMapper objectMapper = new ObjectMapper();
ObjectNode params = objectMapper.createObjectNode();
params.put("image", imageData); // Base64编码的文件内容或者图像URL
// 创建 OkHttpClient 实例
OkHttpClient client = new OkHttpClient();
MediaType JSON = MediaType.Companion.get("application/json; charset=utf-8");
RequestBody body = RequestBody.Companion.create(params.toString(), JSON);
Request request = new Request.Builder()
.url(API_URL)
.post(body)
.build();
// 调用API并处理接口返回数据
try (Response response = client.newCall(request).execute()) {
if (response.isSuccessful()) {
String responseBody = response.body().string();
JsonNode resultNode = objectMapper.readTree(responseBody);
JsonNode result = resultNode.get("result");
String base64Image = result.get("image").asText();
JsonNode texts = result.get("texts");
byte[] imageBytes = Base64.getDecoder().decode(base64Image);
try (FileOutputStream fos = new FileOutputStream(outputImagePath)) {
fos.write(imageBytes);
}
System.out.println("Output image saved at " + outputImagePath);
System.out.println("\nDetected texts: " + texts.toString());
} else {
System.err.println("Request failed with code: " + response.code());
}
}
}
}
package main
import (
"bytes"
"encoding/base64"
"encoding/json"
"fmt"
"io/ioutil"
"net/http"
)
func main() {
API_URL := "http://localhost:8080/ocr"
imagePath := "./demo.jpg"
outputImagePath := "./out.jpg"
// 对本地图像进行Base64编码
imageBytes, err := ioutil.ReadFile(imagePath)
if err != nil {
fmt.Println("Error reading image file:", err)
return
}
imageData := base64.StdEncoding.EncodeToString(imageBytes)
payload := map[string]string{"image": imageData} // Base64编码的文件内容或者图像URL
payloadBytes, err := json.Marshal(payload)
if err != nil {
fmt.Println("Error marshaling payload:", err)
return
}
// 调用API
client := &http.Client{}
req, err := http.NewRequest("POST", API_URL, bytes.NewBuffer(payloadBytes))
if err != nil {
fmt.Println("Error creating request:", err)
return
}
res, err := client.Do(req)
if err != nil {
fmt.Println("Error sending request:", err)
return
}
defer res.Body.Close()
// 处理接口返回数据
body, err := ioutil.ReadAll(res.Body)
if err != nil {
fmt.Println("Error reading response body:", err)
return
}
type Response struct {
Result struct {
Image string `json:"image"`
Texts []map[string]interface{} `json:"texts"`
} `json:"result"`
}
var respData Response
err = json.Unmarshal([]byte(string(body)), &respData)
if err != nil {
fmt.Println("Error unmarshaling response body:", err)
return
}
outputImageData, err := base64.StdEncoding.DecodeString(respData.Result.Image)
if err != nil {
fmt.Println("Error decoding base64 image data:", err)
return
}
err = ioutil.WriteFile(outputImagePath, outputImageData, 0644)
if err != nil {
fmt.Println("Error writing image to file:", err)
return
}
fmt.Printf("Image saved at %s.jpg\n", outputImagePath)
fmt.Println("\nDetected texts:")
for _, text := range respData.Result.Texts {
fmt.Println(text)
}
}
using System;
using System.IO;
using System.Net.Http;
using System.Net.Http.Headers;
using System.Text;
using System.Threading.Tasks;
using Newtonsoft.Json.Linq;
class Program
{
static readonly string API_URL = "http://localhost:8080/ocr";
static readonly string imagePath = "./demo.jpg";
static readonly string outputImagePath = "./out.jpg";
static async Task Main(string[] args)
{
var httpClient = new HttpClient();
// 对本地图像进行Base64编码
byte[] imageBytes = File.ReadAllBytes(imagePath);
string image_data = Convert.ToBase64String(imageBytes);
var payload = new JObject{ { "image", image_data } }; // Base64编码的文件内容或者图像URL
var content = new StringContent(payload.ToString(), Encoding.UTF8, "application/json");
// 调用API
HttpResponseMessage response = await httpClient.PostAsync(API_URL, content);
response.EnsureSuccessStatusCode();
// 处理接口返回数据
string responseBody = await response.Content.ReadAsStringAsync();
JObject jsonResponse = JObject.Parse(responseBody);
string base64Image = jsonResponse["result"]["image"].ToString();
byte[] outputImageBytes = Convert.FromBase64String(base64Image);
File.WriteAllBytes(outputImagePath, outputImageBytes);
Console.WriteLine($"Output image saved at {outputImagePath}");
Console.WriteLine("\nDetected texts:");
Console.WriteLine(jsonResponse["result"]["texts"].ToString());
}
}
const axios = require('axios');
const fs = require('fs');
const API_URL = 'http://localhost:8080/ocr'
const imagePath = './demo.jpg'
const outputImagePath = "./out.jpg";
let config = {
method: 'POST',
maxBodyLength: Infinity,
url: API_URL,
data: JSON.stringify({
'image': encodeImageToBase64(imagePath) // Base64编码的文件内容或者图像URL
})
};
// 对本地图像进行Base64编码
function encodeImageToBase64(filePath) {
const bitmap = fs.readFileSync(filePath);
return Buffer.from(bitmap).toString('base64');
}
// 调用API
axios.request(config)
.then((response) => {
// 处理接口返回数据
const result = response.data["result"];
const imageBuffer = Buffer.from(result["image"], 'base64');
fs.writeFile(outputImagePath, imageBuffer, (err) => {
if (err) throw err;
console.log(`Output image saved at ${outputImagePath}`);
});
console.log("\nDetected texts:");
console.log(result["texts"]);
})
.catch((error) => {
console.log(error);
});
<?php
$API_URL = "http://localhost:8080/ocr"; // 服务URL
$image_path = "./demo.jpg";
$output_image_path = "./out.jpg";
// 对本地图像进行Base64编码
$image_data = base64_encode(file_get_contents($image_path));
$payload = array("image" => $image_data); // Base64编码的文件内容或者图像URL
// 调用API
$ch = curl_init($API_URL);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
$response = curl_exec($ch);
curl_close($ch);
// 处理接口返回数据
$result = json_decode($response, true)["result"];
file_put_contents($output_image_path, base64_decode($result["image"]));
echo "Output image saved at " . $output_image_path . "\n";
echo "\nDetected texts:\n";
print_r($result["texts"]);
?>