Embedded Artificial Intelligence (EAI) integrates AI technologies with resource-constrained embedded systems, overcoming the limitations of cloud AI in aspects such as latency and energy consumption, thereby empowering edge devices with autonomous decision-making and real-time intelligence. This review provides a comprehensive overview of this rapidly evolving field, systematically covering its definition, hardware platforms, software frameworks and tools, core algorithms (including lightweight models), and detailed deployment processes. It also discusses its widespread applications in key areas like autonomous driving and smart Internet of Things (IoT), as well as emerging directions. By analyzing its core challenges and innovative opportunities in algorithms, hardware, and frameworks, this review aims to provide relevant researchers and developers with a practical guidance framework, promoting technological innovation and adoption.

Processing ancient text images presents significant challenges due to severe visual degradation, missing glyph structures, and various types of noise caused by aging. These issues are particularly prominent in Chinese historical documents and stone inscriptions, where diverse writing styles, multi-angle capturing, uneven lighting, and low contrast further hinder the performance of traditional OCR techniques. In this paper, we propose a unified neural framework, UniText, for the detection, recognition, and glyph restoration of Chinese characters in images of historical documents and inscriptions. UniText operates at the character level and processes full-page inputs, making it robust to multi-scale, multi-oriented, and noise-corrupted text. The model adopts a multi-task architecture that integrates spatial localization, semantic recognition, and visual restoration through stroke-aware supervision and multi-scale feature aggregation. Experimental results on our curated dataset of ancient Chinese texts demonstrate that UniText achieves a competitive performance in detection and recognition while producing visually faithful restorations under challenging conditions. This work provides a technically scalable and generalizable framework for image-based document analysis, with potential applications in historical document processing, digital archiving, and broader tasks in text image understanding.

Embedded Artificial Intelligence (EAI) integrates AI technologies with resource-constrained embedded systems, overcoming the limitations of cloud AI in aspects such as latency and energy consumption, thereby empowering edge devices with autonomous decision-making and real-time intelligence. This review provides a comprehensive overview of this rapidly evolving field, systematically covering its definition, hardware platforms, software frameworks and tools, core algorithms (including lightweight models), and detailed deployment processes. It also discusses its widespread applications in key areas like autonomous driving and smart Internet of Things (IoT), as well as emerging directions. By analyzing its core challenges and innovative opportunities in algorithms, hardware, and frameworks, this review aims to provide relevant researchers and developers with a practical guidance framework, promoting technological innovation and adoption.

Artificial intelligence (AI) currently exhibits considerable potential within the realm of biodiversity conservation. However, high-quality regionally customized datasets remain scarce, particularly within urban environments. The existing large-scale bird image datasets often lack a dedicated focus on endangered species endemic to specific geographic regions, as well as a nuanced consideration of the complex interplay between urban and natural environmental contexts. Therefore, this paper introduces Macao-ebird, a novel dataset designed to advance AI-driven recognition and conservation of endangered bird species in Macao. The dataset comprises two subsets: (1) Macao-ebird-cls, a classification dataset with 7341 images covering 24 bird species, emphasizing endangered and vulnerable species native to Macao; and (2) Macao-ebird-det, an object detection dataset generated through AI-agent-assisted labeling using grounding DETR with improved denoising anchor boxes (DINO), significantly reducing manual annotation effort while maintaining high-quality bounding-box annotations. We validate the dataset’s utility through baseline experiments with the You Only Look Once (YOLO) v8–v12 series, achieving a mean average precision (mAP50) of up to 0.984. Macao-ebird addresses critical gaps in the existing datasets by focusing on region-specific endangered species and complex urban–natural environments, providing a benchmark for AI applications in avian conservation.

Real-time monitoring of endangered birds on edge AI hardware is constrained by a structural mismatch between modern lightweight detectors and mainstream NPU deployment toolchains. Recent attention-based detectors rely heavily on dynamic-shape operators that fall back to the host CPU on embedded NPUs, negating the advantages of lightweight architectures. To address this, we propose eBirdNet-Nano, a 1.05 M-parameter detector derived from YOLOv12n through a three-level NPU-friendly redesign: a static NPUConv block at the operator level, an NPU-C3k2 module together with an NPU-SE-Block at the module level, and a balanced 64-channel detection head at the head level. The resulting model achieves a 59% parameter reduction over YOLOv12n at only 5.8 GFLOPs while attaining an mAP@0.5 of 0.929 on a curated 24-species endangered-bird dataset collected in Macao. We further evaluate the model across four heterogeneous edge platforms—the Rockchip RK3588 (ARM + NPU), Kendryte K230 (RISC-V + KPU), Raspberry Pi 4B (pure ARM), and LicheePi 4A (pure RISC-V)—to characterize its behavior under distinct execution models. On the RK3588 NPU under INT8 quantization, eBirdNet-Nano delivers 13.83 ms inference latency and 26.76 ms end-to-end latency at 37.4 FPS, attaining the best parameter–latency balance and the highest parameter-normalized throughput (35.62 FPS/M) among six nano-scale YOLO variants, with an overall 3.53× end-to-end speedup over the YOLOv12n FP16 baseline that decomposes into a 2.97× architectural factor and a 1.19× quantization factor. Integrated into the EbirdEye field terminal, the same model sustains 23.5 ms thread-level end-to-end latency during live operation while supporting approximately 13.5 h of battery-powered runtime per charge. The proposed design offers a practical pathway toward deployable, low-power AI terminals for endangered-species conservation in resource-constrained field environments.