PMC

A) Natural cast of the track LCR15.1p. B) LCR15.4p preserved as a true track. C) Natural cast of the track LCR16.2p. D) Natural cast of the track LCR16.4p. E) LCR17.2pm? preserved as true track. F) Natural cast of the track LCR17.2p. G) LCR18.6p preserved as true track. H) Natural cast of the track LCR18.8?p. I) LCR8.4m preserved as true track with the infilling of the overlying level. J) LCR15.2m preserved as true track. Scale in A, C, D, F, H, J  = 15 cm. Scale in B, G, I  = 8 cm. Scale in E  = 5 cm.

(a) Input Frame (b) The 2^nd component of the input frame containing more dominant information of railway track (c) Recognized obstacle on the railway track using Faster R-CNN (d) Final Recognized Railway Track and obstacles in the frame using Faster R-CNN (e) Recognized obstacle on the railway track using SSD (f) Final Recognized Railway Track and obstacles in the frame using SSD (g) Recognized obstacle on the railway track using Yolov2 (h) Final Recognized Railway Track and obstacles in the frame using Yolov2 (i) Recognized obstacle on the railway track using Yolov5 (j) Final Recognized Railway Track and obstacles in the frame using Yolov5 (k) Input Frame (j) Recognized obstacle in the frame using Yolov5 (without 2D-SSA)

(A) Two possibly associated, seemingly tridactyl and mesaxonic tracks, preserved as concave epireliefs, alongside a possible horsetail stem in cross section (circular structure, top right) and a tiny crocodyliform left pes track (to the right of the large green circle). (B) Two tracks, preserved as concave epireliefs, made by a crocodyliform walking underwater (Hatcherichnus: AODF 904.C1.31–32), that have disrupted the ridges on the displacement rim of the sauropod left pes track AODF 904.S1.07, implying that the crocodyliform traversed the site after the sauropod. (C) ?Wintonopus pes track, preserved as an infilled concave epirelief. (D) ?Turtle track, preserved as an infilled concave epirelief. (E) ?Turtle track, preserved as a partially infilled concave epirelief. (F) ?Wintonopus pes track, preserved as an infilled concave epirelief. (G) ?Turtle track, preserved as a transmitted track through overlying fine sandstone. (H) ?Turtle track, preserved as a transmitted track through overlying fine sandstone.

(A) Activity of short track neurons on the short track (left), long track (middle) and the cross correlation of population vectors on each track (right). (B) Same as (A) but with long track neuron population. (C) Venn diagram showing the overlap of neural populations. The majority of neurons is active on both tracks with only a small fraction being active on exclusively one or the other. (D) Location reconstruction error using only short track or long track neurons on the respective opposite track is slightly, but not significantly larger compared to the same track (mean reconstruction error_short/short: 3.04 ± 0.55, error_short/long: 3.75 ± 3.75; error _long/long: 2.93 ± 0.44, error _long/short: 4.22 ± 0.65; unpaired t-test short track active neurons: p=0.39, long track active neurons: p=0.1). (E) Stacked bar chart trial type selectivity index [(Response_short – Response_long)/(Response_short + Response_long)] for all three cell types.