ESP32 CAM Object Detection & Identification with OpenCV

By Mamtaz AlamUpdated:August 23, 202332 Comments7 Mins Read

Overview: ESP32 CAM Based Object Detection & Identification

This tutorial introduces the topic of ESP32 CAM Based Object Detection & Identification with OpenCV. OpenCV is an open-sourced image processing library that is very widely used not just in industry but also in the field of research and development.

Here for object detection, we have used the cvlib Library. The library uses a pre-trained AI model on the COCO dataset to detect objects. The name of the pre-trained model is YOLOv3.

In this tutorial, we will go through its features, pins description and the method to program ESP32 Camera Module using FTDI Module. We will also set up the Arduino IDE for the ESP32 Camera Module. We will also upload the firmware and then work on the object detection & identification part. The script for object detection is written in the python programming language, thus we will also have to install Python and its required Libraries.

In an earlier ESP32 CAM Based project we learned about Face Detection System & also Color Detection System using Python & OpenCV. This project also requires the use of OpenCV for Object Detection & Identification.

Bill of Materials

The following is the list of Bill of Materials for building an ESP32 CAM Based Object Detection & Identification System. TheESP32 CAM when combined with other hardware & firmware track and identify the object.You can purchase all these components from Amazon.

S.N.	Components	Quantity	Purchase Links
1	ESP32-CAM Board AI-Thinker	1	Amazon \| AliExpress
2	FTDI Module	1	Amazon \| AliExpress
3	Micro-USB Cable	1	Amazon \| AliExpress
4	Jumper Wires	10	Amazon \| AliExpress

ESP32 CAM Module

The ESP32 Based Camera Module developed by AI-Thinker. The controller is based on a 32-bit CPU & has a combined Wi-Fi + Bluetooth/BLE Chip. It has a built-in 520 KB SRAM with an external 4M PSRAM. Its GPIO Pins have support like UART, SPI, I2C, PWM, ADC, and DAC.

The module combines with the OV2640 Camera Module which has the highest Camera Resolution up to 1600 × 1200. The camera connects to the ESP32 CAM Board using a 24 pins gold plated connector. The board supports an SD Card of up to 4GB. The SD Card stores capture images.

To learn in detail about the ESP32 Camera Module you can refer to our previous Getting Started Tutorial.

ESP32-CAM FTDI Connection

The board doesn’t have a programmer chip. So In order to program this board, you can use any type of USB-to-TTL Module. There are so many FTDI Module available based on CP2102 or CP2104 Chip or any other chip.

Make a following connection between FTDI Module and ESP32 CAM module.

ESP32-CAM	FTDI Programmer
GND	GND
5V	VCC
U0R	TX
U0T	RX
GPIO0	GND

Connect the 5V & GND Pin of ESP32 to 5V & GND of FTDI Module. Similarly, connect the Rx to UOT and Tx to UOR Pin. And the most important thing, you need to short the IO0 and GND Pin together. This is to put the device in programming mode. Once programming is done you can remove it.

Project PCB Gerber File & PCB Ordering Online

If you don’t want to assemble the circuit on a breadboard and you want PCB for the project, then here is the PCB for you. The PCB Board for ESP32 CAM Board is designed using EasyEDA online Circuit Schematics & PCB designing tool. The PCB looks something like below.

The Gerber File for the PCB is given below. You can simply download the Gerber File and order the PCB from ALLPCB at 1$ only.

Download Gerber File: ESP32-CAM Multipurpose PCB

You can use this Gerber file to order high quality PCB for this project. To do that visit the ALLPCB official website by clicking here: https://www.allpcb.com/.

You can now upload the Gerber File by choosing the Quote Now option. From these options, you can choose the Material Type, Dimensions, Quantity, Thickness, Solder Mask Color and other required parameters.

After filling all details, select your country and shipping method. Finally you can place the order.

You can assemble the components on the PCB Board.

Installing ESP32CAM Library

Here we will not use the general ESP webserver example rather another streaming process. Therefore we need to add another ESPCAM library. The esp32cam library provides an object oriented API to use OV2640 camera on ESP32 microcontroller. It is a wrapper of esp32-camera library.

Go to the following Github Link and download the zip library as in the image

Once downloaded add this zip library to Arduino Libray Folder. To do so follow the following steps:
Open Arduino -> Sketch -> Include Library -> Add .ZIP Library… -> Navigate to downloaded zip file -> add

Source Code/Program for ESP32 CAM Module

Here is a source code for Object Detection & Identification with ESP32 Camera & OpenCV. Copy the code and paste it in the Arduino IDE.

#include <WebServer.h>

#include <WiFi.h>

#include <esp32cam.h>

const char* WIFI_SSID = "ssid";

const char* WIFI_PASS = "password";

WebServer server(80);

static auto loRes = esp32cam::Resolution::find(320, 240);

static auto midRes = esp32cam::Resolution::find(350, 530);

static auto hiRes = esp32cam::Resolution::find(800, 600);

void serveJpg()

{

auto frame = esp32cam::capture();

if (frame == nullptr) {

Serial.println("CAPTURE FAIL");

server.send(503, "", "");

return;

}

Serial.printf("CAPTURE OK %dx%d %db\n", frame->getWidth(), frame->getHeight(),

static_cast<int>(frame->size()));

server.setContentLength(frame->size());

server.send(200, "image/jpeg");

WiFiClient client = server.client();

frame->writeTo(client);

}

void handleJpgLo()

{

if (!esp32cam::Camera.changeResolution(loRes)) {

Serial.println("SET-LO-RES FAIL");

}

serveJpg();

}

void handleJpgHi()

{

if (!esp32cam::Camera.changeResolution(hiRes)) {

Serial.println("SET-HI-RES FAIL");

}

serveJpg();

}

void handleJpgMid()

{

if (!esp32cam::Camera.changeResolution(midRes)) {

Serial.println("SET-MID-RES FAIL");

}

serveJpg();

}

void setup(){

Serial.begin(115200);

Serial.println();

{

using namespace esp32cam;

Config cfg;

cfg.setPins(pins::AiThinker);

cfg.setResolution(hiRes);

cfg.setBufferCount(2);

cfg.setJpeg(80);

bool ok = Camera.begin(cfg);

Serial.println(ok ? "CAMERA OK" : "CAMERA FAIL");

}

WiFi.persistent(false);

WiFi.mode(WIFI_STA);

WiFi.begin(WIFI_SSID, WIFI_PASS);

while (WiFi.status() != WL_CONNECTED) {

delay(500);

}

Serial.print("http://");

Serial.println(WiFi.localIP());

Serial.println(" /cam-lo.jpg");

Serial.println(" /cam-hi.jpg");

Serial.println(" /cam-mid.jpg");

server.on("/cam-lo.jpg", handleJpgLo);

server.on("/cam-hi.jpg", handleJpgHi);

server.on("/cam-mid.jpg", handleJpgMid);

server.begin();

}

void loop()

{

server.handleClient();

}

Before Uploading the code you have to make a small change to the code. Change the SSID and password variable and in accordance with your WiFi network.

Now compile and upload it to the ESP32 CAM Board. But during uploading, you have to follow few steps every time.

Make sure the IO0 pin is shorted with the ground when you have pressed the upload button.
If you see the dots and dashes while uploading press the reset button immediately
Once the code is uploaded, remove the I01 pin shorting with Ground and press the reset button once again.
If the output is the Serial monitor is still not there then press the reset button again.

Now you can see a similar output as in the image below.

Here, copy the IP address visible, we will be using it to edit the URL in python code

Python Library Installation

For the live stream of video to be visible on our computer we need to write a Python script that will enable us to retrieve the frames of the video. The first step is to install Python. Go to python.org and download Python.

Once download, install Python.
Then Go to the command prompt and install NumPy, OpenCV and cvlib libraries.

type: pip install numpy and press enter. After the installation is done.
type: pip install opencv-python and press enter.
type: pip install cvlib and press enter, close the command prompt.

In our python code we have used urllib.request to retrieve the frames from the URL and the library for image processing is OpenCV. For Object detection, we have used the Cvlib library that uses an AI model for detecting objects. Since the whole process requires a good amount of processing power, thus we have used multiprocessing which utilizes multiple cores of our CPU.

Python Code for ESP32 CAM Object Detection/Identification

Now open Idle code editor or any other python code editor.

Copy and paste the code from below and do the replacements as mentioned below.

import cv2

import matplotlib.pyplot as plt

import cvlib as cv

import urllib.request

import numpy as np

from cvlib.object_detection import draw_bbox

import concurrent.futures

url='http://192.168.10.162/cam-hi.jpg'

im=None

def run1():

cv2.namedWindow("live transmission", cv2.WINDOW_AUTOSIZE)

while True:

img_resp=urllib.request.urlopen(url)

imgnp=np.array(bytearray(img_resp.read()),dtype=np.uint8)

im = cv2.imdecode(imgnp,-1)

cv2.imshow('live transmission',im)

key=cv2.waitKey(5)

if key==ord('q'):

break

cv2.destroyAllWindows()

def run2():

cv2.namedWindow("detection", cv2.WINDOW_AUTOSIZE)

while True:

img_resp=urllib.request.urlopen(url)

imgnp=np.array(bytearray(img_resp.read()),dtype=np.uint8)

im = cv2.imdecode(imgnp,-1)

bbox, label, conf = cv.detect_common_objects(im)

im = draw_bbox(im, bbox, label, conf)

cv2.imshow('detection',im)

key=cv2.waitKey(5)

if key==ord('q'):

break

cv2.destroyAllWindows()

if __name__ == '__main__':

print("started")

with concurrent.futures.ProcessPoolExecutor() as executer:

f1= executer.submit(run1)

f2= executer.submit(run2)

Here we have to replace the IP address with the IP on Arduino Serial Monitor. For the first time, it will install a few files if they are not existing.

Once we have done that we can see two windows named live transmission and detected is visible.

Now in the detected window, one can view different detected objects as around them different colored boxes are visible.

Applications

Object detection is having uses in almost all sorts of industries. It is used for tracking objects, people counting, automated CCTV surveillance, vehicle detection, etc.

These are just some basic examples but in reality, the potential is tremendous.

Video Tutorial & Guide

Object Detection & Identification using ESP32 CAM Module & OpenCV

Watch this video on YouTube.

You may use AMB82-Mini IoT AI Camera for powerful object detection and identification even without using the Python Code.

Previous ArticleRaspberry Pi Pico Primer Kit for Beginners & Students – 10 Projects

Next Article Interfacing MAX17043 LiPo Fuel Gauge IC with Arduino

View 32 Comments

32 Comments

Markus Togi Fedrian Rivaldi Sinaga on November 8, 2021 9:52 PM

Excuse mr / ms

Sorry for my bad English

I’m confusing with teh FTDI? Is it used as the programmable microprocessor?

I’m making school projecs, and I want to use your project as refference.

I don’t have the FTDI module, but I have ESP32 Development Board (the one without the camera) separated with the ESP32 Cam, can my ESP32 Development Board substitute the FTDI?

I’ll be so grateful if you can help me by replying via my email.

Thanks mr/ms.

Reply
Akash on November 10, 2021 8:40 PM

Hello. So basically the FTDI allows you to connect the ESP32(the programmable board) to your PC so that you can upload you board. You use it to transfer your code onto your ESP32. There are also other devices you can use to connect you microprocessor onto the board. For example, a TTL UART

Reply
some_guy on December 4, 2021 8:07 AM

it runs, but the object detection window isn’t responding or showing anything. i’ve done everything in the vid and this guide, even downloaded cudart64_110, what’s happening? what did i do wrong?

Reply
Fernando Carvalho on December 19, 2021 3:16 AM

I have the same problem

Reply
Amir_Eshaqy on December 24, 2021 4:35 PM

hi,
I have this problem in executing Python code, please help
Traceback (most recent call last):

File “C:\Users\Amir_Eshaqy\Desktop\sss.py”, line 3, in
import cvlib as cv

File “C:\Users\Amir_Eshaqy\AppData\Local\Programs\Python\Python310\lib\site-packages\cvlib__init__.py”, line 8, in
from .gender_detection import detect_gender

File “C:\Users\Amir_Eshaqy\AppData\Local\Programs\Python\Python310\lib\site-packages\cvlib\gender_detection.py”, line 3, in
from tensorflow.keras.utils import get_file

ModuleNotFoundError: No module named ‘tensorflow’

Thank you

Reply
Cemil on January 20, 2022 6:49 PM

İt about the version of Python. Install the 3.9 and install the tensorflow library.

Reply
Chris Ellingson on January 29, 2022 2:40 PM

Thank you for the informative write-up.

I’m waiting for my ESP32 CAM modules to ship.

Can this detection system distinguish between different animals of the same species? I am working on a remotely-operated tick treatment sprayer to dose the bush buck living on the smallholding. There are several of them and they are individually distinct enough in coloration and size.

I would like to automate the process as the bush buck tend to sporadically pass through a gate in the early morning and evenings when I am not around to control the sprayer. Having a system that can identify each animal and dose appropriate amounts of tick treatment would help massively to reduce the tick load in the bush. Having it avoid spraying people and young bush buck automatically would be a benefit too.

Reply
al06825AL on February 19, 2022 12:01 PM

Hello… I upgraded ESP32 to 1.0.6 (latest). Keeps getting this error from your esp32cam.cpp.

\esp32cam-main\src\esp32cam.cpp: In member function ‘esp32cam::ResolutionList esp32cam::CameraClass::listResolutions() const’:
\esp32cam-main\src\esp32cam.cpp:30:3: error: ‘camera_sensor_info_t’ was not declared in this scope
camera_sensor_info_t* info = esp_camera_sensor_get_info(&sensor->id);
^
\esp32cam-main\src\esp32cam.cpp:30:25: error: ‘info’ was not declared in this scope
camera_sensor_info_t* info = esp_camera_sensor_get_info(&sensor->id);
^
\esp32cam-main\src\esp32cam.cpp:30:70: error: ‘esp_camera_sensor_get_info’ was not declared in this scope
camera_sensor_info_t* info = esp_camera_sensor_get_info(&sensor->id);

Reply
skeerthan98gmailcom on February 22, 2022 2:35 PM

I too am getting the same error. Does anyone know the solution to this problem?

Reply
Prithvi on March 1, 2022 8:51 PM

Iam also getting the same error. There is some problem in the installed esp32cam library…….anyone pls help

Reply
ToddC on March 11, 2022 11:26 PM

looks like camera_sensor_info_t has changed in the new version, raise an issue in the git repo

Reply
Fattymcnugget on March 16, 2022 2:36 AM

Updating the esp module to 2.02 fixes the issue link bellow on how to installhttps://docs.espressif.com/projects/arduino-esp32/en/latest/installing.html

Reply
Sashi Kiran on April 5, 2022 10:39 PM

hello iam getting this error while executing the code can any one please help me to solve this

C:\Users\Bala Krishna\Documents\Arduino\libraries\esp32cam-main\src\esp32cam.cpp: In member function ‘esp32cam::ResolutionList esp32cam::CameraClass::listResolutions() const’:

C:\Users\Bala Krishna\Documents\Arduino\libraries\esp32cam-main\src\esp32cam.cpp:30:3: error: ‘camera_sensor_info_t’ was not declared in this scope

camera_sensor_info_t* info = esp_camera_sensor_get_info(&sensor->id);

^

C:\Users\Bala Krishna\Documents\Arduino\libraries\esp32cam-main\src\esp32cam.cpp:30:25: error: ‘info’ was not declared in this scope

camera_sensor_info_t* info = esp_camera_sensor_get_info(&sensor->id);

C++

1
2

<code> ^
</code>

C:\Users\Bala Krishna\Documents\Arduino\libraries\esp32cam-main\src\esp32cam.cpp:30:70: error: ‘esp_camera_sensor_get_info’ was not declared in this scope

camera_sensor_info_t* info = esp_camera_sensor_get_info(&sensor->id);

C++

1
2

<code> ^
</code>

Multiple libraries were found for “WiFi.h”
Used: C:\Users\Bala Krishna\AppData\Local\Arduino15\packages\esp32\hardware\esp32\1.0.6\libraries\WiFi
Not used: C:\Program Files (x86)\Arduino\libraries\WiFi
exit status 1
Error compiling for board ESP32 Wrover Module.

Reply
JL on April 10, 2022 4:51 PM

You might be using an older version of the esp32 library. You can use this link for additional boards manager. You should be using 2.0.2 version.https://github.com/espressif/arduino-esp32/releases/download/2.0.2/package_esp32_index.json

Reply
wahyu on April 17, 2022 10:52 PM

hello, sorry to ask why when my python program is running it says unterminated string literal (detected at line 9)

Reply
wahyu on April 17, 2022 11:24 PM

hello, I want to ask why when my python program runs it says unterminated string literal (detected on line 9)

Reply
Ke_S on April 21, 2022 1:35 AM

Hello,
did you find a solution, i have the same problem

Reply
Indian Guy on April 23, 2022 10:51 AM

you can upload code to esp32 with arduno also

Reply
nlac on September 24, 2022 8:21 AM

“ESP32 CAM Based Object Detection” problem is, the object detection has nothing to do with ESP32 here, since it runs on the pc so the title is misleading. People who are searching for this topic, usually want to run the detecting itself on the ESP32(-CAM),

Reply
aparna on November 25, 2022 2:55 AM

hey hi do u have any reference code how to submit ESP32-CAM image to openalpr.com for license plate reading

Reply
Pascua Kurt on February 24, 2023 2:04 AM

Hi, I want to ask if the system can work using the Arduino UNO because I use the Arduino UNO and not the FTDI module because it’s not connecting to my ESP32 Cam, also when I use the Arduino UNO to get the IP address of the ESP32 Cam and run the python code that you use in your recent video the live transmission is not showing up but the IDLE is printing that the live transmission of the ESP32 Cam is running. Do you know why is this happening?

Reply
vijay siva on February 28, 2023 2:06 AM

Receiving the error esp32 cam has not been declared.
arduino ide2.0.3

Reply
Manickarajan on March 15, 2023 5:43 AM

I too have same problem. Anybody can help me?

Reply
GIRINATH V P on March 15, 2023 8:32 AM

Hey.. I do everything, live video window also visible, but the detection window shows not responding. What would I do
….

Reply
manh on May 14, 2023 11:06 AM

hi pro i also have same error, are you fix problem? and can you guide me fix it ?

Reply
mukil on June 22, 2023 11:13 AM

do you found the error?

Reply
mukil on June 22, 2023 11:56 AM

for me both windows appeared but suddenly it disappeared

Reply
mukilan j on June 22, 2023 11:57 AM

for me both windows appeared but suddenly it disappeared

Reply
sughosh on June 27, 2023 2:01 PM

Thank you for this wonderful project, but is there a way that we can add a speaker that outputs the data or the image recognized by the camera? basically, the speak has to output the object seen. is that possible to do that?
Thank you

Reply
Ammar Khan on July 20, 2023 5:46 AM

Have you solved this problem ?

Reply
whats-updog on February 2, 2024 1:47 PM

Is there a solution for the non responding detection window ? Thx

Reply
- ekko ekko on May 4, 2024 6:42 AM
  
  have you soved it ? i got same error , too . detection is not responding .
  
  Reply