Object Detection, Tracking and Analytics using Pretrained ML models (Yolo V7-8, Yolo NAS, Deepsort)
Budget: $750 – $1,500 AUD
Object Detection, Tracking, and Analytics Project
- Primary Purpose: Object Detection, Tracking, and Analytics using pretrained AI models such as Yolo v5-8, Deepsort, Detectron 2, deeplabcut etc. All these models are available on Github with pretrained weights. Three key AI functionalities I'm after are object detection and tracking, posture detection and tracking and human/animal behaviour analysis. The interface should be able to allow basic basic selection of region/area on the input data to collect relevant statistics. The selection could be a line or a rectangular region on the image/video to collect statistics such as number of objects (distinct classes) passed through in either direction, heatmap showing concentration of distinct (selected classes from a list of detected ones) over time, path trajectory of selected classes in different colours to understand the motion behaviour, etc.
The interface could be a simple GUI in windows to run on a GPU. Realtime processing is important especially when using Yolo family models. There are enough examples of all the requirements above and associated codes on the Github. I need a centralised interface that could seamlessly use different ml models on the same input (image, video, webcam, stream) and produce desired statistics. Some of the applications of this tool in mind are traffic behaviour monitoring, sports analytics, human/animal/insects behaviour for scientific studies.
- Desired Level of Accuracy: Moderate accuracy with some false positives
- ML Model Preference: The client has models in mind that are required
Skills and Experience:
- Experience in implementing object detection, tracking, and analytics using pretrained ML models such as Yolo V5-8, Yolo_NAS, detectron 2, Deepsort and deeplabcut.
- Strong understanding of computer vision and machine learning algorithms
- Proficiency in Python and relevant libraries/frameworks (e.g., TensorFlow, PyTorch)
- Ability to fine-tune and optimize ML models for desired accuracy and performance
- Experience in working with video data and real-time processing
- Knowledge of retail analytics and customer behavior analysis is a plus
- Primary Purpose: Object Detection, Tracking, and Analytics using pretrained AI models such as Yolo v5-8, Deepsort, Detectron 2, deeplabcut etc. All these models are available on Github with pretrained weights. Three key AI functionalities I'm after are object detection and tracking, posture detection and tracking and human/animal behaviour analysis. The interface should be able to allow basic basic selection of region/area on the input data to collect relevant statistics. The selection could be a line or a rectangular region on the image/video to collect statistics such as number of objects (distinct classes) passed through in either direction, heatmap showing concentration of distinct (selected classes from a list of detected ones) over time, path trajectory of selected classes in different colours to understand the motion behaviour, etc.
The interface could be a simple GUI in windows to run on a GPU. Realtime processing is important especially when using Yolo family models. There are enough examples of all the requirements above and associated codes on the Github. I need a centralised interface that could seamlessly use different ml models on the same input (image, video, webcam, stream) and produce desired statistics. Some of the applications of this tool in mind are traffic behaviour monitoring, sports analytics, human/animal/insects behaviour for scientific studies.
- Desired Level of Accuracy: Moderate accuracy with some false positives
- ML Model Preference: The client has models in mind that are required
Skills and Experience:
- Experience in implementing object detection, tracking, and analytics using pretrained ML models such as Yolo V5-8, Yolo_NAS, detectron 2, Deepsort and deeplabcut.
- Strong understanding of computer vision and machine learning algorithms
- Proficiency in Python and relevant libraries/frameworks (e.g., TensorFlow, PyTorch)
- Ability to fine-tune and optimize ML models for desired accuracy and performance
- Experience in working with video data and real-time processing
- Knowledge of retail analytics and customer behavior analysis is a plus
Related categories:
C Programming
Business, Accounting, Human Resources & Legal
Python
Algorithm
C++ Programming