Pedestrian- and Vehicle-Detection Algorithm Based on Improved Aggregated Channel Features

Abstract

In advanced driver-assistance systems (ADAS), the accuracy and real-time performance of pedestrian-and vehicle-detection algorithms based on vision sensors are crucial for safety. Here, a lightweight detection algorithm based on aggregated channel features (ACFs),consisting of a context pixel ACF (CP-ACF) pedestrian detector and a multiview ACF (Mv-ACF) vehicle detector, is proposed to rapidly and precisely understand road scenes. The former fuses local and context information to improve the robustness to pedestrian deformation, while the latter contains a number of subclass detectors to alleviate intraclass differences due to different viewing angles. Compared to the original ACF, the CP-ACF pedestrian detector reduces the average miss rate (AMR) by 6.34%. The Mv-ACF vehicle detector improves the average precision (AP) by 40.26% on average at easy, moderate and hard levels. This remarkable effectiveness is due to the spectrum clustering of multiview samples and the resulting integration of these subclass detectors via confidence score calibration, which reduces the intraclass differences of vehicles. Since feature extraction takes up 68.8% of the total detection time, a mechanism of feature sharing between pedestrian and vehicle detectors is advanced to reduce the time spent in feature extraction. A strategy based on ground-plane constraints (GPCs) is proposed to control false detection of pedestrians and vehicles by incorporating road prior information, which reduces the AMR by 1.07% for CP-ACF pedestrian detectors and improves the AP by 0.27% on average for Mv-ACF vehicle detectors. Thus, the proposed algorithm can effectively control false detection by road prior information.

Vulnerable Road Users and Connected Autonomous Vehicles Interaction: A Survey

“…Machine learning algorithms focus on feature extraction and classifiers [92]. For feature extraction, techniques such as Histogram of Oriented Gradients [93][94][95][96][97][98][99][100], Local Binary Pattern [101][102][103][104][105][106][107], Deformable Part Model [108][109][110][111][112][113], and Aggregate Channel Feature (ACF) [114][115][116][117][118] are included. On the other hand, methods such as Support Vector Machine (SVM) [94,105,[119][120][121][122], Decision Tree [123][124][125][126], Random Forest (RF) [127][128][129][130][131][132] and Ada-Boost [81,119,133,134] are used for ...…”

GLFNet: Combining Global and Local Information in Vehicle Re-Recognition

“…With the continuous advancement of computer vision technology, the field of road traffic is rapidly progressing towards informatization, efficiency, safety, and intelligence [ 1 , 2 , 3 ]. In surveillance videos, vehicles, as crucial targets, have garnered widespread attention in computer vision, encompassing tasks such as recognition [ 4 , 5 ], detection [ 6 ], and classification [ 7 ]. The primary objective of vehicle re-identification (Re-ID) [ 8 , 9 , 10 , 11 , 12 ] is to accurately identify the same vehicle corresponding to a given detected vehicle in surveillance videos across different scenarios or time periods.…”

Pedestrian detection system based on deep learning

“…Two of all useful information are the detection and location of pedestrians in front of a vehicle. Traditional object detection techniques in the past were based on are based on handcrafted features such as integral channel features (ICF) [1], [2], scale-invariant feature transform (SIFT) [3], histogram of oriented gradients (HOG) [4], local binary patterns (LBP) [5], general forward-backward (GFB) [6] ,and their variations [7]- [9] and combinations [10], [11], followed by a trainable classifier such as support vector machines (SVM) [7], [12], boosted classifiers [13], or random forests [14]. Their performance can be easily degraded by constructing complex ensembles that combine numerous low-level features with high-level context from object detectors and scene classifiers.…”