{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:55:31Z","timestamp":1774540531224,"version":"3.50.1"},"reference-count":34,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2021,2,2]],"date-time":"2021-02-02T00:00:00Z","timestamp":1612224000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>Great achievements have been made in pedestrian detection through deep learning. For detectors based on deep learning, making better use of features has become the key to their detection effect. While current pedestrian detectors have made efforts in feature utilization to improve their detection performance, the feature utilization is still inadequate. To solve the problem of inadequate feature utilization, we proposed the Multi-Level Feature Fusion Module (MFFM) and its Multi-Scale Feature Fusion Unit (MFFU) sub-module, which connect feature maps of the same scale and different scales by using horizontal and vertical connections and shortcut structures. All of these connections are accompanied by weights that can be learned; thus, they can be used as adaptive multi-level and multi-scale feature fusion modules to fuse the best features. Then, we built a complete pedestrian detector, the Adaptive Feature Fusion Detector (AFFDet), which is an anchor-free one-stage pedestrian detector that can make full use of features for detection. As a result, compared with other methods, our method has better performance on the challenging Caltech Pedestrian Detection Benchmark (Caltech) and has quite competitive speed. It is the current state-of-the-art one-stage pedestrian detection method.<\/jats:p>","DOI":"10.3390\/fi13020038","type":"journal-article","created":{"date-parts":[[2021,2,2]],"date-time":"2021-02-02T05:44:42Z","timestamp":1612244682000},"page":"38","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Adaptive Weighted Multi-Level Fusion of Multi-Scale Features: A New Approach to Pedestrian Detection"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8546-5189","authenticated-orcid":false,"given":"Yao","family":"Xu","sequence":"first","affiliation":[{"name":"College of Electrical Engineering, Sichuan University, Chengdu 610065, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering, Sichuan University, Chengdu 610065, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,2,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23\u201328). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016). Ssd: Single shot multibox detector. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21\u201326). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., and Girshick, R. (2017, January 7\u201313). Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Cai, Z., and Vasconcelos, N. (2018, January 18\u201323). Cascade r-cnn: Delving into high quality object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref_8","unstructured":"Dai, J., Li, Y., He, K., and Sun, J. (2016). R-fcn: Object detection via region-based fully convolutional networks. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhang, L., Lin, L., Liang, X., and He, K. (2016). Is faster R-CNN doing well for pedestrian detection?. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-46475-6_28"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Cai, Z., Fan, Q., Feris, R.S., and Vasconcelos, N. (2016). A unified multi-scale deep convolutional neural network for fast object detection. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wang, X., Xiao, T., Jiang, Y., Shao, S., Sun, J., and Shen, C. (2018, January 18\u201323). Repulsion loss: Detecting pedestrians in a crowd. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00811"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 7\u201313). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Liu, W., Liao, S., Hu, W., Liang, X., and Chen, X. (2018, January 8\u201314). Learning efficient single-stage pedestrian detectors by asymptotic localization fitting. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01264-9_38"},{"key":"ref_14","unstructured":"Huang, L., Yang, Y., Deng, Y., and Yu, Y. (2015). Densebox: Unifying landmark localization with end to end object detection. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Law, H., and Deng, J. (2018, January 8\u201314). Cornernet: Detecting objects as paired keypoints. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Lu, X., Li, B., Yue, Y., Li, Q., and Yan, J. (2019, January 15\u201321). Grid r-cnn. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00754"},{"key":"ref_18","unstructured":"Tian, Z., Shen, C., Chen, H., and He, T. (November, January 27). Fcos: Fully convolutional one-stage object detection. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_19","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., and Tian, Q. (November, January 27). Centernet: Keypoint triplets for object detection. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Liu, W., Liao, S., Ren, W., Hu, W., and Yu, Y. (2019, January 15\u201321). High-level semantic feature detection: A new perspective for pedestrian detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00533"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","article-title":"Res2Net: A New Multi-Scale Backbone Architecture","volume":"43","author":"Gao","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.T., and Sun, J. (2018, January 8\u201314). Shufflenet v2: Practical guidelines for efficient cnn architecture design. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Wojek, C., Schiele, B., and Perona, P. (2009). Pedestrian detection: A benchmark. 2009 IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPRW.2009.5206631"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhang, S., Benenson, R., Omran, M., Hosang, J., and Schiele, B. (2016, January 27\u201330). How far are we from solving pedestrian detection?. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.141"},{"key":"ref_25","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019, January 8\u201314). PyTorch: An Imperative Style, High-Performance Deep Learning Library. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_26","unstructured":"Micikevicius, P., Narang, S., Alben, J., Diamos, G., Elsen, E., Garcia, D., Ginsburg, B., Houston, M., Kuchaiev, O., and Venkatesh, G. (2017). Mixed precision training. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_28","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_29","unstructured":"Tarvainen, A., and Valpola, H. (2017, January 4\u20139). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_30","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.neucom.2015.01.043","article-title":"DLANet: A manifold-learning-based discriminative feature learning network for scene classification","volume":"157","author":"Feng","year":"2015","journal-title":"Neurocomputing"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhang, S., Yang, J., and Schiele, B. (2018, January 18\u201323). Occluded pedestrian detection through guided attention in cnns. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00731"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Mao, J., Xiao, T., Jiang, Y., and Cao, Z. (2017, January 21\u201326). What can help pedestrian detection?. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.639"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.simpat.2019.03.005","article-title":"Ar-ped: A framework of augmented reality enabled pedestrian-in-the-loop simulation","volume":"94","author":"Perez","year":"2019","journal-title":"Simul. Model. Pract. Theory"}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/13\/2\/38\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:18:42Z","timestamp":1760159922000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/13\/2\/38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,2]]},"references-count":34,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,2]]}},"alternative-id":["fi13020038"],"URL":"https:\/\/doi.org\/10.3390\/fi13020038","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,2]]}}}