Optimized Object Detection in Road‐Vehicle Images Using Approximate Tree Multiplier‐Based Daubechies Wavelet Transform and YOLO Variant

ABSTRACT Object detection in road‐vehicle images presents significant challenges due to variations in view angle, weather conditions, shooting height, noise, low contrast, geometric distortions, and atmospheric effects. The research proposes a novel methodology integrating Deep Learning and optimization techniques to enhance object detection performance. To address image quality issues, a Gaussian Blur with a Bilateral filter is employed for noise reduction and contrast enhancement. For feature extraction, a Lightweight Tree Multiplier–based Discrete Daubechies Wavelet Transform Convolutional Network is introduced, utilizing an advanced wavelet transform approach to capture both spatial and spectral features effectively. Feature selection is optimized using Adaptive Quantum‐Informed Recursive Multiscale Feature Selection, incorporating Quantum‐Informed Recursive Optimization to retain the most relevant features while reducing redundancy. For object detection, the extracted features are processed through the Improved Lightweight Harris Hawks YOLOv11 Network, for efficient and high‐speed object detection. Improved Harris Hawks Optimization is also applied to optimize the loss function, enhancing detection accuracy. The outcomes of the implementation reached a precision rate of 99.8% and an accuracy rate of 99.7%. The model that proposed intends to be a powerful tool for the detection of road vehicles in difficult images, giving short processing time together with high‐detection efficiency and reliability.