get in touch

How Computer Vision in Agriculture Helps Track Bee Population and Health

Computer Vision in Agriculture

How Computer Vision in Agriculture Helps Track Bee Population and Health

Timspark used AI to make mobile computer vision software to track the beehive life. We also predict how the bee population will grow and how healthy it is overall.

#AI

#MobileDevelopment

#ComputerVision

Client*

It was Timspark’s internal project. We were eager to independently grow expertise in Machine Learning and built an ML-powered app with prediction functionality for agriculture.

Project in numbers

duration

6 months

team

4 specialists

Team involved in the project

industry

Agriculture

solution

Mobile computer vision software for beehive tracking

technologies

Python, PyTorch, YOLOv3, Google Cloud Platform, DigitalOcean, Swift 5

1 x Lead Data Scientist

1 x iOS Developer

1 x Data Engineer

1 x Project Manager

1 x QA

HIRE THE TEAM

Challenge

Our team did it all for this project – from planning the product’s architecture to labeling the data and training the neural network. This hands-on approach to computer vision services helped us become experts in the field and led to a fully working product as the outcome. We tackled a set of machine learning challenges and industry-related standards of using computer vision in agriculture, too.

Solution & functionality

Our ready-made solution is a mobile app that uses computer vision in agriculture to count bees in the hive accurately. It also creates user-friendly charts and graphs, making it easy to monitor the hive’s growth and health.

Object detection for beehive population count and health tracking

We have harnessed object recognition technology, so now it is possible to scan and instantly figure out how many bees are in the hive. Also, the solution helps distinguish the regular bees from the queen bees.

A modern user-friendly mobile app

Our team built mobile computer vision software from the ground up with an easy-to-use interface. We also added a feature where a client can get automatic reports about the hive’s status using the information uploaded.

Results and business value

We’ve successfully crafted computer vision solutions for iOS, designed to assist beekeepers in caring for their beehives more effectively.

Benefits 

Our app offers a major time-saving advantage. With traditional manual inspections taking up to an hour per beehive, our computer vision services help beekeepers inspect a hive in just 10 minutes or even less.

Related cases

see all case studies

We appreciate your interest in Timspark

    Optimizing KYC Framework for iOS and Android

    Identification mobile app

    Optimizing KYC Framework for iOS and Android

    Our team upgraded identity mobile apps for iOS and Android and optimized their key verification and access management functions.

    #Banking

    #MobileDevelopment

    #DataProtection

    Client*

    Our customer is a European software-as-a-service (SaaS) organization offering solutions for establishing and executing Know Your Customer (KYC), Know Your Business (KYB), and Anti-Money Laundering (AML) procedures in external services.

    *We cannot provide any information about the client or specifics of the case study due to non-disclosure agreement (NDA) restrictions.

    Project in numbers

    duration

    1 year

    team

    5 specialists

    efforts

    11 520 hours

    Team involved in the project

    industry

    Banking, Information Technology

    solution

    Identification app

    technologies

    Native Android (Kotlin), Native iOS (Swift), Cross-platform Flutter (Dart)/RN (JS)

    1 x Web Developer

    1 x Android Developer

    1 x Product Manager

    1 x QA specialist  

    1 x iOS developer

    HIRE THE TEAM

    Challenge

    The main objective is to optimize the KYC framework for iOS and Android. The application had a slow validation process, and the web widget had restricted functionality. Therefore, it was not fully optimized for iOS and Android platforms. Our team was assigned to upgrade the KYC library and enhance the critical authentication capabilities.

    Related objectives

    Address issues with Android and iOS SDKs

    Leverage unclear documentation for Nexus ID Check

    Leverage documentation for the web version

    Redesign and optimize the framework architecture

    Solution & functionality

    Our team collaborated closely with the customer to guarantee a smooth integration of SDKs into the new multi-platform application and native applications. We successfully improved the Nexus ID Check system, reorganized the library structure and framework for Android and iOS, and included a new library.

    Redesigned architecture and improved functionality

    Our experts have optimized the Nexus ID Check capabilities on Android and iOS platforms. We updated the system by eliminating redundant screens and conducted UI refinements. The updates resulted in faster and more user-friendly verification processes.

    Thanks to redesigning the mobile framework, we reduced the time for implementing new features by 30% and simplified code maintenance. Furthermore, we introduced guidelines for integrating React Native and Flutter, facilitating the use of this library in future cross-platform solutions.

    New FaceTec SDK for enhanced 3D biometrics

    Before the update, our facial recognition software supported only regular recognition methods. Users had to capture multiple photos of their faces from different angles. The 2D images were sent to the Nexus ID Check server for further processing.

    Our team seamlessly integrated an upgraded FaceTec SDK library to boost biometric processing. With FaceTec, the biometric data collection process has become more user-friendly and less time-consuming. The interface provides clear instructions for users, simplifying the scanning procedure and getting high-quality biometric data. When acquired, the data is processed and validated on the server’s side.

    Besides optimizing the scanning and verification processes per se, our team enhanced the image quality, which led to more accurate user identification.

    Optimized document verification solution

    Previously, users could only add supporting documents on mobile devices by taking a photo in real time using their phone camera. However, we have now implemented a new function that allows users to take pictures in any convenient screen orientation, add various documentation types, and upload documents directly from their phone gallery in multiple formats, including PDF. This enhancement simplifies the verification process for users as they no longer need to keep physical documents on hand to take photos each time they log in.

    Instant document verification and user identification

    Before optimization, users were limited to adding supporting documents on mobile devices through real-time photo capture with their phone cameras. With the new feature, users are enabled to take photos in any suitable screen orientation and easily upload various document types directly from their phone gallery in multiple formats, including PDF.

    With biometric data and supporting documents, users had to upload them every time they logged into the application. An instant user identification system allows users to log in quickly using a simple face scan. The uploaded selfies are instantly verified against verified 3D biometrics and other data stored in the backend system. Users are free from the need to re-upload documents and biometric data each time they log in.

    Results and business value

    The resulting cross-platform app now has a wide array of features aimed at enhancing KYC (know your customer), KYB (know your business), and AML (anti-money laundering) functionalities:

    Innovative face biometrics capture

    Easy data upload for the users

    Enhanced data collection on the user’s geolocation

    Enhanced accuracy and verification process

    The system architecture and functionality of the KYC solution on mobile devices was refined with the advanced FaceTec SDK library and incorporated 3D biometrics. The team enhanced both the verification process and the user interface.

    Related cases

    see all case studies

    We appreciate your interest in Timspark

      Mobile Banking App Development: Applications as a Digital Wallet

      E-payment platform
      Mobile Banking App Development: Applications as a Digital Wallet
      Our team developed iOS and Android applications from the ground up, with instant payment functionalities (P2P, C2B, B2B) and banking account management.
      #Banking
      #MobileDevelopment

      Client*

      Our client is a large IT company providing software development and IT consulting services for businesses and organizations, selected as a general contractor for a government project, Therefore the government financial regulator acted as the end customer.
      *We cannot provide any information about the client or specifics of the case study due to non-disclosure agreement (NDA) restrictions.

      Project in numbers

      duration
      2+ years
      team
      12 specialists
      efforts
      10 000+ hours

      Team involved in the project

      industry
      Banking, Information Technology
      product
      E-payment platform
      technologies
      ?
      6 x Developers
      ?
      1 x Business analyst
      ?
      1 x Project manager
      ?
      2 x QA specialists
      ?
      1 x Solution architect
      ?
      1 x UX/UI Designer
      HIRE THE TEAM

      Challenge

      The major objective for the team was to create a transparent and easy-to-use digital system for instant electronic payments with modules for personal data security, fraud protection, and others.

      Related objectives

      Digital payment infrastructure
      Availability of financial services
      Resilient system security
      Effective fraud detection

      Solution & functionality

      In order to protect confidential data, we integrated a multi-factor security system using data encryption, TLS 1.2, SSL Pinning, and checking for rooted devices. The processing itself is performed by a third party.

      Smooth user experience

      As it was crucial to guarantee an immersive user journey, we backed the smartphone solution with a range of essential characteristics and capacities.
      Our development team has enhanced the mobile application with extensive payment options. Users can make transfers and payments (via QR codes as well) on an account-to-account basis by account number, email or mobile phone number. Individual and corporate users can replenish their accounts, as well as make requests for payment (for instance, to split the bill).

      Digital wallet inside the application

      To use the app, customers are required to connect their bank card/s and undergo the authentication process, providing details such as the bank’s name, account number/card information. The amount of cards the user can link, regional or foreign, is unlimited. After the registration and veri?cation process, users get access to the digital wallet.

      Personalization

      The app gives users flexibility and a range of personal budgeting features. Thus, it allows users to check the payments record, get detailed reports on incoming and outcoming transactions, set goals, and receive notifications to be on top of the spending limits.

      Results and business value

      The team implemented a user-friendly e-payment application ecosystem with integrated modules and launched iOS and Android apps within the set deadline. The final product was successfully used by citizens of the whole country and tourists.
      System with top-level security
      High-performing iOS and Android apps
      User-friendly interface
      Feature-rich functionality
      Customer satisfaction
      The team got positive feedback from both the customer and the end-user on the exceptional standard of development and efficiency of the app, as well as the effective communication throughout the project.

      Related cases

      see all case studies

      We appreciate your interest in Timspark

        Let’s build something great together

          Let’s build something great together

            Let’s build something great together

              Let’s build something great together