Tensorflow Object Detection API Research Articles

FOOD CLASSIFICATION AND CALORIE ESTIMATION USING CNN

This research paper explores the transformative impact of deep learning methodologies in the domains of food image recognition, classification, and calorie estimation. By utilizing the convergence of machine learning with convolutional neural networks (CNNs), the study tackles the growing concerns surrounding obesity and health difficulties, highlighting the need for creative methods of nutritional monitoring. Motivated by challenges in fruit classification and the limitations of traditional methods, the research progressively shifts towards efficient and accurate image-based approaches, particularly highlighting the effectiveness of CNNs. The methodology focuses on machine learning-based approaches for food calorie estimation, with a specific emphasis on parameter-optimized lightweight CNN models utilizing TensorFlow's Object Detection API and CNN. The results showcase impressive accuracy levels, often exceeding 90%, across diverse food items, albeit with persistent challenges such as limited datasets, computational costs, and real-world application constraints. In conclusion, this comprehensive review underscores the transformative potential of deep learning in fostering healthier lifestyles, combating obesity, and providing valuable insights for dietary guidance and health management. Further research is recommended to enhance dataset representativeness and optimize model generalization for broader practical applicability Keywords: Calorie estimation, Classification, Convolutional neural network, Object detection.

SURVEY ON FOOD CLASSIFICATION AND CALORIE ESTIMATION USING CNN

This research paper explores the transformative impact of deep learning methodologies in the domains of food image recognition, classification, and calorie estimation. By utilizing the convergence of machine learning with convolutional neural networks (CNNs), the study tackles the growing concerns surrounding obesity and health difficulties, highlighting the need for creative methods of nutritional monitoring. Motivated by challenges in fruit classification and the limitations of traditional methods, the research progressively shifts towards efficient and accurate image-based approaches, particularly highlighting the effectiveness of CNNs. The methodology focuses on machine learning-based approaches for food calorie estimation, with a specific emphasis on parameter-optimized lightweight CNN models utilizing TensorFlow's Object Detection API and Mask R-CNN. The results showcase impressive accuracy levels, often exceeding 90%, across diverse food items, albeit with persistent challenges such as limited datasets, computational costs, and real-world application constraints. In conclusion, this comprehensive review underscores the transformative potential of deep learning in fostering healthier lifestyles, combating obesity, and providing valuable insights for dietary guidance and health management. Further research is recommended to enhance dataset representativeness and optimize model generalization for broader practical applicability Keywords: Calorie estimation, Classification, Convolutional neural network, Object detection.

Применение нейронных сетей для диагностики устройств контактной сети: современные подходы и перспективы

The article discusses the prospects of using neural networks for information processing in the field of diagnostics of contact network devices. An overview of software and modern methods using neural networks has been presented, an analysis of software complexes based on fundamentally new methods of data processing obtained during the diagnosis of a contact network has been carried out. For further research, promising software solutions used for analyzing photo and video files have been noted: OpenCV, TensorFlow Object Detection API, YOLO, Amazon Rekognition Video и IBM Watson Visual Recognition.

Artificial intelligent identification of apatite fission tracks based on machine learning

Over the past half century, apatite fission track (AFT) thermochronometry has been widely used in the studies of thermal histories of Earth’s uppermost crust. The acquired thermal histories in turn can be used to quantify many geologic processes such as erosion, sedimentary burial, and tectonic deformation. However, the current practice of acquiring AFT data has major limitations due to the use of traditional microscopes by human operators, which is slow and error-prone. This study uses the local binary pattern feature based on the OpenCV cascade classifier and the faster region-based convolutional neural network model based on the TensorFlow Object Detection API, these two methods offer a means for the rapid identification and measurement of apatite fission tracks, leading to significant improvements in the efficiency and accuracy of track counting. We employed a training dataset consisting of 50 spontaneous fission track images and 65 Durango standard samples as training data for both techniques. Subsequently, the performance of these methods was evaluated using additional 10 spontaneous fission track images and 15 Durango standard samples, which resulted in higher Precision, Recall, and F1-Score values. Through these illustrative examples, we have effectively demonstrated the higher accuracy of these newly developed methods in identifying apatite fission tracks. This suggests their potential for widespread applications in future apatite fission track research.

Classifying BISINDO Alphabet using TensorFlow Object Detection API

Indonesian Sign Language (BISINDO) is one of the sign languages used in Indonesia. The process of classifying BISINDO can be done by utilizing advances in computer technology such as deep learning. The use of the BISINDO letter classification system with the application of the MobileNet V2 FPNLite SSD model using the TensorFlow object detection API. The purpose of this study is to classify BISINDO letters A-Z and measure the accuracy, precision, recall, and cross-validation performance of the model. The dataset used was 4054 images with a size of consisting of 26 letter classes, which were taken by researchers by applying several research scenarios and limitations. The steps carried out are: dividing the ratio of the simulation dataset 80:20, and applying cross-validation (k-fold = 5). In this study, a real time testing using 2 scenarios was conducted, namely testing with bright light conditions of 500 lux and dim light of 50 lux with an average processing time of 30 frames per second (fps). With a simulation data set ratio of 80:20, 5 iterations were performed, the first iteration yielded a precision result of 0.758 and a recall result of 0.790, and the second iteration yielded a precision result of 0.635 and a recall result of 0.77, then obtained an accuracy score of 0.712, the third iteration provides a recall score of 0.746, the fourth iteration obtains a precision score of 0.713 and a recall score of 0.751, the fifth iteration gives a precision score of 0.742 for a fit score case and the recall score is 0.773. So, the overall average precision score is 0.712 and the overall average recall score is 0.747, indicating that the model built performs very well.

Deep learning based object detection and surrounding environment description for visually impaired people

Object detection, one of the most significant contributions of computer vision and machine learning, plays an immense role in identifying and locating objects in an image or a video. We recognize distinct objects and precisely get their information through object detection, such as their size, shape, and location. This paper developed a low-cost assistive system of obstacle detection and the surrounding environment depiction to help blind people using deep learning techniques. TensorFlow object detection API and SSDLite MobileNetV2 have been used to create the proposed object detection model. The pre-trained SSDLite MobileNetV2 model is trained on the COCO dataset, with almost 328,000 images of 90 different objects. The gradient particle swarm optimization (PSO) technique has been used in this work to optimize the final layers and their corresponding hyperparameters of the MobileNetV2 model. Next, we used the Google text-to-speech module, PyAudio, playsound, and speech recognition to generate the audio feedback of the detected objects. A Raspberry Pi camera captures real-time video where real-time object detection is done frame by frame with Raspberry Pi 4B microcontroller. The proposed device is integrated into a head cap, which will help visually impaired people to detect obstacles in their path, as it is more efficient than a traditional white cane. Apart from this detection model, we trained a secondary computer vision model and named it the “ambiance mode.” In this mode, the last three convolutional layers of SSDLite MobileNetV2 are trained through transfer learning on a weather dataset. The dataset comprises around 500 images from four classes: cloudy, rainy, foggy, and sunrise. In this mode, the proposed system will narrate the surrounding scene elaborately, almost like a human describing a landscape or a beautiful sunset to a visually impaired person. The performance of the object detection and ambiance description modes are tested and evaluated in a desktop computer and Raspberry Pi embedded system. Detection accuracy and mean average precision, frame rate, confusion matrix, and ROC curve measure the model's accuracy on both setups. This low-cost proposed system is believed to help visually impaired people in their day-to-day life.

Traffic Lights Detection and Recognition with New Benchmark Datasets Using Deep Learning and TensorFlow Object Detection API

Today, traffic lights are widely used in places with high vehicle traffic. Especially in autonomous vehicles, fast and high accuracy detection and recognition of traffic lights are critical. Machine learning methods are generally used to do this. Deep learning models give more successful results than machine learning methods in detecting the exact location of traffic lights in different climatic conditions. In this study, Faster R-CNN Inception v2 deep learning model was trained and tested on two different datasets that we prepared and published publicly under variable traffic and climatic conditions in Turkey. Successful results were obtained with fewer data by using the Transfer Learning method with the help of TensorFlow Object Detection API in the training of the model. It has been shown that the datasets we have prepared can be developed considering the conditions in other countries and successful results will be obtained.

A novel YOLOv4‐modified approach for efficient object detection in satellite imagery

AbstractInterpreting high‐resolution satellite imagery could be an expensive and time‐consuming task for human eyes. Computer Vision and Deep Learning techniques can help to solve this major problem by applying detection algorithms, which can ease the task of analysing such images for the benefit of humans. It can help in changing the way we comprehend and anticipate the economic activity around the world. Such techniques help us to observe the urban development in high security areas such as national and international borders. Constant progressions in improving and making satellites deployment, a cost‐effective process to strengthen the networks of satellite orbiting the earth is one of the reasons such tasks can be easily solved with the help of high‐resolution images. Current computer vision research works have achieved significant milestones in accuracy and speed but, there are still room for improvements. In this paper, we addressed some of these methods to bring them to a combined pipeline and proposed a set of improvements to further improve the speed and the accuracy of the detections. We proposed a unified framework, which combines several object detection algorithms and the state‐of‐art architecture of YoloV4 along with the TensorFlow object detection API. This framework can detect small and well as large objects with improved speed and accuracy by using two detectors for different scales. Evaluation ran on these high‐resolution images yield mAP of 85.6% F1‐score of 0.84.

American Sign Language Translator

Abstract: Sign language is one of the ancient and most natural form of language for communication. Sign Language is being used by many people in the world, but only a small part of the population knows how to interpret the language. Which makes it tough for the Deaf people to communicate with other people. We used the Tensorflow object detection API in our research, which is an open-source framework for training and deploying object detection models.

Instance segmentation scheme for roofs in rural areas based on Mask R-CNN

Rooftop detection has numerous applications such as change detection in human settlements, land encroachments, planning routes to rural areas and estimation of solar generation potential of cities. Detecting the number, type and shape of building roofs form part of preliminary procedures to perform a variety of tasks for making decisions. Assessment of rooftops in rural areas is an important task in the estimation of potential solar generation and sizing of solar PV systems which has proven to be very challenging due to the different quality, lighting conditions and resolution of aerial and satellite images. In this research, we implement a mask RCNN algorithm using TensorFlow Object Detection API to detect the rooftop of buildings in a typical rural settlement. The average precision and recall values (@ IoU = 0.5:0.05:0.95) of the trained model were 85% and 88.2% respectively. The results of the experiment show that the approach can effectively and accurately detect and segment rural rooftops from high-resolution aerial images.

Azerbaijani sign language recognition using machine learning approach

Abstract Sign Language recognition is one of the essential and focal areas for researchers in terms of improving the integration of speech and hearing-impaired people into common society. The main idea is to detect the hand gestures of impaired people and convert them to understandable formats, such as text by leveraging advanced approaches. In this paper, we present our contribution to the improvement of Azerbaijani Sign Language (AzSL). We worked on AzSL Alphabet static signs real-time recognition. The method applied in this work is Object Classification and Recognition by leveraging pre-trained lightweight Convolutional Neural Networks models. At first, a dataset containing near to 1000 images has been collected, then interesting objects on images have been labeled with bounding boxing option. To build, train, evaluate and deploy the relevant model, TensorFlow Object Detection API with Python has been employed. MobileNet v2 pre-trained model has been leveraged for this task. In the trial experiment with four sign classes (A, B, C, E) and 5000 step numbers 15.2% training loss and 83% evaluation mean average precision results have been obtained. In the next step of model deployment experiments with all 24 static signs of AzSL, 49700 and 27700 steps (180 and 100 epochs, respectively) 6.4% and 18.2% training losses, 66.5% and 71.6% mAP outcomes gained, respectively.

Real Time Object Detection using SSD and MobileNet

Abstract: This Accurate Real-time object detection needs faster computation power to identify the object at that specific time. The accuracy of object detection has increased drastically with the advancement of deep learning techniques. We incorporate a stateof-the-art method for object detection to achieve high accuracy with real-time performance. The state-of-the-art methods are subdivided into two types. The first is one-stage methods that prioritize inference speed, and example models include YOLO, SSD, and RetinaNet. The second is two-stage methods that prioritize detection accuracy, and its example models include Faster R-CNN, Mask R-CNN, and Cascade R-CNN. Among all these, Faster-RCNN and SSD have better accuracy, while YOLO performs better when speed is given preference over accuracy. A major challenge in many of the object detection systems is that it is dependent on the other computer vision techniques for helping the deep learning-based approach, which results in slow and non-optimal performance. In this paper, we have used a deep learning-based approach to solve the matter of object detection in an end-to-end fashion. Deep learning combines SSD and Mobile Nets to perform the efficient implementation of detection and tracking.SSD eliminates the feature resampling stage and combined all calculated results as a single component. MobileNet is a lightweight network model that uses depth-wise separable convolution for the places which lacks computational power like mobile devices (eg: laptop, mobile phones, etc). This algorithm performs efficient object detection while not compromising on the performance The main purpose of our research is to elaborate the accuracy of an object detection method SSD and the importance of the pre-trained deep learning model MobileNet. The resultant system is fast and accurate, thus aiding those applications which require object detection Keywords: Object Detection, CNN, TensorFlow object detection API, SSD with MobileNet

Blind Person Assistant: Object Detection

Abstract: It’s a known fact that estimated number of blind persons in the world is about 285 million, approximately equal to the 20% of the Indian Population. They are mostly dependent on someone for even accessing their basic daily needs. In our project, we used TensorFlow, it's a new library from Google. TensorFlow model our neural networks. The TensorFlow Object Detection API is used to detect many objects. We have Introduce an algorithm (SSD). SSD uses a similar phase while training, to match the appropriate anchor box with the bounding boxes of each ground truth object within an image. Essentially, the anchor box with the highest degree of flap with an object is responsible for predicting that object's class and its location. It has microcontroller which has wi-fi inbuilt module. This guide is convenient and offers data to the client to move around in new condition, regardless of whether indoor or open air, through an ease to use interface. Then again, and so as to lessen route challenges of the visually impaired, a deterrent location framework utilizing ultrasounds is added to this gadget. The proposed framework identifies the closest hindrance through ultrasonic sensors and it gives an alert to illuminate the visually impaired about its confinement. Keywords: Object Detection, Blind Person, location, ultrasonic sensors, gadget

Deep based learning: ebin sorting system development

Vietnam was the fifth country that dumped more plastic into the oceans than the rest of the world combined. The country produces an average of 25.5 million tons of waste per year, of which 75% is buried. Several burial sites in major cities such as Hanoi, Ho Chi Minh city, and Da Nang city are overloaded and negatively affecting citizens’ lives. Therefore, sorting at source would significantly reduce soil resources and groundwater pollution and save money on collection costs, transportation, treatment, and easing the pressure on the landfills. Using computer vision may help classify easily recyclable trash into different categories based on its material. This paper proposes an experiment on a customed Convolution Neural Network (CNN) based waste detector for three classes of trash: Plastic bottles, Cans, and Glass. The study used up to 900 hand-collected image data separated into 500 for analysis and 400 remains for assessing the result. All trashed objects used for generating data were collected around the Ho Chi Minh city University of Technology (HCMUT, Vietnam). The Deep Learning model used in this research, named SSD MobileNet V2, is part of the open-source Tensorflow Object Detection API. The system gave the result, the relative match percentage of different amounts of data we fed the model. The system showed linear relativity between the amount of data trained AI100, AI200, AI300, AI400, AI500, and the mean Average Precision (mAP) when testing the system. From this on, the study conducted another experiment to ensure that the performance of the trained model would meet expectations, AI401. In this experiment, the system showed over 80% inaccuracy overall. By back-analysis, this paper would be a good vision for researchers to study and enhance the system’s accuracy to serve the purpose of trash classification in innovative trash bin applications.

Counting of exposed aggregate number on pavement surface based on computer vision technique

Functional performance of exposed aggregate concrete pavement (EACP), such as tyre-pavement noise, is influenced by the surface texture depth and wavelength. To minimise tyre-pavement noise, the texture wavelength, which is represented by the exposed aggregate number (EAN), should be controlled. Normally, the EAN is conducted by manual counting. It requires much human efforts. Therefore, this study suggests an efficient method to count the EAN on a digital image of EACP surface through the deep learning model faster region-based convolutional neural network (Faster R-CNN). The TensorFlow Object Detection API was used to adjust the parameters in the training model. Results of the suggested model were compared with the manual counting in the mock-up and field test dataset. The result showed that the mean absolute error was 5.34 and 8.19 for the mock-up and field tests, respectively. Therefore, the proposed method can be used to preliminarily estimate the EAN under specified condition.

Vehicle Detection and Traffic Prediction

Abstract: On the road, vehicle detection processes are utilized for vehicle tracking, vehicle counting, vehicle speed, and traffic analysis. For vehicle detection, the Tensorflow object detection API method is employed. The Object Detection API in Tensorflow is a powerful tool that allows anyone to easily design and deploy effective picture recognition applications. Another way to control traffic is to use a traffic control system. Multiple linear regression is utilized to regulate the traffic system, while the OpenCV approach is used to identify vehicle speed. A system for fine payment is also offered. It makes police officers' jobs easier. The exact results of vehicle speed and traffic control are provided. Keywords: Vehicle detection, Tensorflow object detection API, Multiple linear regression, OpenCV, Fine payment

Motorcycle Apprehension using Deep Learning and K-Nearest Neighbor Algorithm

Abstract — Road violations that lead to accidents and deaths are increasing significantly. There are about 1.35 million people who die every year because of road accidents, and more than half of these involve a motorcycle. Authorities are strictly implementing traffic laws and making some innovations to capture those motorists violating laws easily. Researchers are also doing their part to help solve the problem; indeed, their studies give a vast contribution and solve road safety issues. However, the papers on road violations were focused more on on-road violations involving four-wheeled vehicles. For this reason, a motorcyclist violation detection and plate recognition with e-mail notification using a Deep Learning algorithm were developed to apprehend motorcyclists violating traffic laws. Tensorflow Object Detection API was used as a framework along with the Faster R-CNN model. The system was developed using Anaconda Environment, Python Scripting, KNN, and MySQL Connector. The conditions and criteria for detecting a violation are based on motorcycle detection, including motorcycle tracking. After violation detection and plate recognition, the violation's image is sent through e-mail together with the details of the offense.

Motorcycle Apprehension using Deep Learning and K-Nearest Neighbor Algorithm

Abstract — Road violations that lead to accidents and deaths are increasing significantly. There are about 1.35 million people who die every year because of road accidents, and more than half of these involve a motorcycle. Authorities are strictly implementing traffic laws and making some innovations to capture those motorists violating laws easily. Researchers are also doing their part to help solve the problem; indeed, their studies give a vast contribution and solve road safety issues. However, the papers on road violations were focused more on on-road violations involving four-wheeled vehicles. For this reason, a motorcyclist violation detection and plate recognition with e-mail notification using a Deep Learning algorithm were developed to apprehend motorcyclists violating traffic laws. Tensorflow Object Detection API was used as a framework along with the Faster R-CNN model. The system was developed using Anaconda Environment, Python Scripting, KNN, and MySQL Connector. The conditions and criteria for detecting a violation are based on motorcycle detection, including motorcycle tracking. After violation detection and plate recognition, the violation's image is sent through e-mail together with the details of the offense.

A Novel Automated Tree Detection System using Faster R-CNN

This paper introduces an approach to tree detection using mapped aerial images from drones. Tree detection is achieved by training a Faster Region-Based Convolutional Neural Network using Tensorflow Object Detection API. A Color-Based tree detector is also added to further filter out undesired detections such as tree shadows. Aerial images obtained from drones are mapped using Web Open Drone Map, an open-source drone mapping software. This paper aims to achieve a low-cost approach to disaster assessment using tree detection and drone images. The implemented system is able to detect trees and yielded an average detection rate accuracy of 85.63% and 95.14% for stitched maps and unstitched images respectively.

Phenotypic evaluation of Brown Swiss dairy cattle using images processing

Phenotypic evaluation of Brown Swiss cows is a method used in the Peruvian Andean Region to identify and select breeding females. Selection is based on their closeness to ideal dairy conformation. This task is perform by a specialists in stock judging. Under this context, the aim of the present study was to demonstrate the feasibility to perform a partial phenotypic evaluation of Brown Swiss cows by overlapping templates through development of a cow detection model and a decision making support system for identification and automatic classification of Brown Swiss cattle. TensorFlow Object Detection API was used to detect the cow in real time. The learning transfer approach was used for training, and MobilNet was selected as a pre-trained architecture. As result a mobile app was developed to determine whether an animal has Brown Swiss breed phenotypic characteristics through an automatic adjustment and calibration of a cow's template.