DCSP-RCNN: A Network for Person Detection with Color, Size and Pattern Characteristic Parsing
Nov 1, 2023·,
,,·
1 min read
Abhilash SK
Nischal DS
Shiv Kumar
Venu Nookala
Karthik S
Abstract
DCSP-RCNN extends person detection by jointly parsing color, size, and pattern characteristics alongside bounding boxes. Modeling these attributes explicitly helps disambiguate people in crowded scenes and supports attribute-aware downstream tasks such as retrieval and tracking. The network predicts person masks and per-pixel color, size, and pattern descriptors simultaneously, enabling robust detection when color or scale varies.
Type
Publication
2023 International Conference on Recent Advances in Information Technology for Sustainable Development (ICRAIS)
Status
Peer-reviewed
Read the paper on IEEE Xplore.
Authors
Lead Engineer — GenAI / Agentic AI & Applied ML
Lead Engineer with 5 years of hands-on experience developing and deploying GenAI, RAG, Agentic AI, and deep learning systems from scratch. I build production-grade AI platforms for realtime voice interaction, enterprise knowledge retrieval, regulatory search, and automated finance analysis. My work spans NLP, autonomous driving, computer vision, and Camera-LiDAR-Radar fusion, with a focus on reliable architecture, model optimization, and scalable data pipelines.
Stack: Python, GCP, GenAI, LLMs, Agents, Docker, FastAPI, Cloud SQL, Google ADK, Vertex AI, Agent Engine, Cloud Run, OpenAI Realtime API, WebSockets, Redis, MongoDB, Milvus, JWT, Docling, BM25, ModernBERT, vLLM, and FAISS.