Automated biological counting is essential for scaling wildlife monitoring and biodiversity assessments, as manual processing currently limits analytical effort and scalability. This review evaluates the integration of deep learning and computer vision across diverse acquisition platforms, including camera traps, unmanned aerial vehicles (UAVs), and remote sensing. Methodological paradigms ranging from Convolutional Neural Networks (CNNs) and one-stage detectors like You Only Look Once (YOLO) to recent transformer-based architectures and hybrid models are examined. The literature shows that these methods consistently achieve high accuracy—often exceeding 95%—across various taxa, including insect pests, aquatic organisms, terrestrial vegetation, and forest ecosystems. However, persistent challenges such as object occlusion, cryptic species differentiation, and the scarcity of high-quality, labeled datasets continue to hinder fully automated workflows. We conclude that while automated counting has fundamentally increased data throughput, future advancements must focus on enhancing model generalization through self-supervised learning and improved data augmentation techniques. These developments are critical for transitioning from experimental models to robust, operational tools for global ecological monitoring and conservation efforts.
SUMMARY: Plant nuclear genomes contain a variable, though typically minor, fraction of DNA sequences of plastid origin known as NUPTs. Unlike the massive transfer of DNA and genes from the proto‐organelle genome to the nucleus that occurred during the endosymbiotic event that gave rise to plastids, the formation of NUPTs is an ongoing process that does not imply concomitant DNA loss. Although NUPTs are generally considered to be potentially deleterious insertions that are continuously generated and rapidly eliminated at near‐constant turnover rates, accumulating evidence reveals alternative evolutionary trajectories. In this review, we discuss recent findings that highlight the episodic formation of NUPTs, their subsequent proliferation, and their eventual long‐term fixation within the nuclear genome. We also explore their non‐random spatial association with specific genomic elements. NUPTs show preferential overlap with specific superfamilies of transposable elements, which may facilitate their proliferation and dispersal throughout the nuclear genome. Regarding protein‐coding genes, the contribution of NUPTs varies among species. In contrast, NUPTs are found to be consistently enriched among certain classes of non‐coding RNA genes, notably rRNA, tRNA, and specific regulatory RNA families, suggesting that they are involved in the evolution of gene regulation and translational machinery. Overall, these findings underscore the unexpected complexity of the mechanisms underlying NUPT formation and support the idea that they are a significant source of genome variation and evolutionary innovation. Further research is necessary to fully elucidate the mechanisms underlying NUPT formation, as well as to determine their potential adaptive significance in plant genome evolution.