The Firefly Algorithm (FA), while effective for complex optimization, suffers from inherent limitations such as search oscillation and low convergence precision. To address these issues, a firefly algorithm with multiple learning ability based on gender difference (MLFA-GD) is proposed. Firstly, the algorithm evenly divides the randomly initialized population into male and female subgroups. Then a male firefly learning strategy which incorporated a partial attraction model combining with an escape mechanism, and a female firefly learning strategy guided by both the generalized centroid of the male subgroup and the global optimal individual are designed separately. Additionally, a random walk strategy is further incorporated to refine the optimization accuracy. Different from existing gender-based FA variants, male fireflies either fly toward brighter female fireflies or move away from weaker individuals to enhance exploration capability. Meanwhile, female fireflies update positions guided by two elite male individuals, effectively leveraging historical search information to improve exploitation capability. The performance is evaluated on 23 numerical functions, 30 CEC 2017 benchmark functions and an automatic test data generation problem. The experiment comparison results with six FA variants and ten popular meta heuristic algorithms confirm its enhanced search capability and significantly higher optimization precision, validating its effectiveness in balancing exploration and exploitation.

Online multi-object tracking (MOT) aims to maintain consistent target identities across video frames, yet it remains vulnerable to identity switches under occlusion and appearance variation. Many existing trackers rely on single-prototype exponential moving average (EMA) memory, which is efficient but prone to contamination, over-smoothing, and staleness. To address this issue, we propose Hierarchical Multi-Prototype Appearance Memory (HMP), a plug-and-play module for online MOT. HMP separates stable long-term identity anchors from short-term transitional evidence through a multi-prototype long-term memory and a short first-in-first-out (FIFO) queue. A unified joint reliability score governs memory writing and maintenance, and a frozen two-stage association strategy first performs stable primary matching and then allows conservative short-term recovery only on residual cases. Experiments on MOT17 and MOT20 show that HMP improves identity continuity while preserving competitive overall tracking quality. Controlled ablations further support the effectiveness of the proposed memory representation, reliability control, and staged evidence usage under fixed upstream modules.

This paper proposes a frequency-modulated continuous-wave synthetic aperture radar (FMCW-SAR) imaging system for fast target detection. The system’s antenna array improves azimuthal resolution while maintaining low complexity using a 44-element equivalent virtual array and improves the data acquisition efficiency by employing the trigger and MCU control board. A series of improved algorithms are adopted to increase the speed of radar imaging and achieve fast detection. To solve the problem of large data volumes in traditional array antenna switching control methods, an array switching control algorithm is proposed based on the enhanced ordered statistical constant false alarm rate (EOS-CFAR). The data volume is reduced by dividing the array into several subarrays in advance. The echo signals acquired by the array switching control method are not continuous in the azimuthal direction, and data anomalies are handled by interpolating and compensating the received radar data to form compensated periodic data. The coherent background is subtracted from the padded signal using recursive averaging, resulting in high-resolution imaging while improving the data-processing speed. The TensorFlow-based Omega-K algorithm is employed for synthetic aperture radar (SAR) imaging, which customizes the optimization of TensorFlow for array radar signals. For the radar signal phase optimization, an improved Adam Optimizer optimizes the phase of the radar signal to maintain phase smoothing, thereby improving the clarity of the radar image. The Omega-K algorithm is optimized by TensorFlow and accelerated on the GPU to improve the efficiency of the large-scale fast Fourier transform (FFT) and Stolt interpolation operations, which improves the speed of radar imaging and enables fast detection.